{"id":7075,"date":"2017-04-11T07:31:14","date_gmt":"2017-04-11T12:31:14","guid":{"rendered":"https:\/\/vieux.ivado.ca\/?page_id=7075\/"},"modified":"2020-07-07T11:45:32","modified_gmt":"2020-07-07T15:45:32","slug":"postdoctoral-scholarships","status":"publish","type":"page","link":"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/","title":{"rendered":"IVADO postdoctoral funding Program"},"content":{"rendered":"<p><span style=\"color: #ff0000;\"><b>COVID-19 update:<\/b> Important dates for this program have been modified and are identified in red in the information below. Thank you for your understanding.<\/span><\/p>\n<h4 style=\"text-align: center;\"><a href=\"https:\/\/ivado.smapply.io\/\" target=\"_blank\" rel=\"noopener noreferrer\">Apply here &gt;&gt;<\/a><\/h4>\n<p><strong>IVADO\u2019s commitment to equity, diversity and inclusion and note to applicants<\/strong><br \/>\nTo ensure all members of society draw equal benefit from the advancement of knowledge and opportunities in data science, IVADO promotes equity, diversity and inclusion through each of its programs. IVADO aims to provide a recruitment process and research setting that are inclusive, non-discriminatory, open and transparent.<\/p>\n<div class=\"gdlr-shortcode-wrapper\"><div class=\"gdlr-item gdlr-tab-item horizontal\" ><div class=\"tab-title-wrapper\" ><h4 class=\"tab-title active\" ><span>Overview<\/span><\/h4><h4 class=\"tab-title\" ><span>Description<\/span><\/h4><h4 class=\"tab-title\" ><span>FAQ<\/span><\/h4><h4 class=\"tab-title\" ><span>Application<\/span><\/h4><h4 class=\"tab-title\" ><span>Laureates (Winter 2018)<\/span><\/h4><h4 class=\"tab-title\" ><span>Laureates (Fall 2018)<\/span><\/h4><h4 class=\"tab-title\" ><span>Laureates (Winter 2019)<\/span><\/h4><h4 class=\"tab-title\" ><span>Laureates (Fall 2019)<\/span><\/h4><\/div><div class=\"tab-content-wrapper\" ><div class=\"tab-content active\" ><h3 class=\"gdlr-heading-shortcode \"  style=\"color: #000000;font-size: 16px;font-weight: bold;\" >Program description<\/h3>\n<ul>\n<li><strong>Field of study<\/strong>: The IVADO Postdoctoral Funding program supports research on the <a href=\"http:\/\/www.cfref-apogee.gc.ca\/results-resultats\/abstracts-resumes\/competition_2\/universite_de_montreal-eng.aspx\">issues raised in the Canada First funding competition<\/a>: data science in a broad sense, including methodological research in data science (machine learning, operations research, statistics) and its application in a range of sectors including the priority sectors of IVADO (health, transportation, logistics, energy, business and finance) or any other sector of application (sociology, physics, linguistics, engineering, etc.).<\/li>\n<li>Amount of salary (not an award) and grant period:\n<ul>\n<li><b>Regular funding:&nbsp;$70&nbsp;000<\/b> per year (including benefits) for up to <b>two years<\/b>, entirely funded by IVADO.<\/li>\n<li><b>Partnership funding:&nbsp;$70&nbsp;000 <\/b>per year equally funded by <b>IVADO <\/b>($35&nbsp;000)<b> and a partner <\/b>($35&nbsp;000) (including benefits) for up to <b>two years<\/b>.<\/li>\n<li><b><em>&#8220;Fellow&#8221;<\/em> funding:&nbsp;$90&nbsp;000<\/b> per year (including benefits) for up to <b>three years<\/b>, entirely funded by IVADO. In the first year, an additional&nbsp;$10\u00a0000\u00a0may be awarded upon request to cover relocation expenses, along with&nbsp;$15\u00a0000 per year to fund research activities.<\/li>\n<li>Upon request, applicants from countries eligible to receive <a href=\"http:\/\/www.oecd.org\/dac\/financing-sustainable-development\/development-finance-standards\/DAC_List_ODA_Recipients2014to2017_flows_En.pdf\">ODA from Canada<\/a> may be reimbursed for their relocation expenses to begin their postdoctoral training in Montr\u00e9al.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Application deadline<\/strong>: <span style=\"color: #ff0000;\">May 13th, 2020, 11 a.m. EST<\/span><\/li>\n<li><strong>Expected application notification date<\/strong>: August 2020<\/li>\n<li><strong>Criteria<\/strong>: See description tab<\/li>\n<li><strong>Submission<\/strong>: See submission tab<\/li>\n<li><strong>Information<\/strong>: <a href=\"mailto:programmes-excellence@ivado.ca\">programmes-excellence@ivado.ca<\/a><\/li>\n<\/ul>\n<\/div><div class=\"tab-content\" ><p><span style=\"font-weight: 400;\"><\/p>\n<h3 class=\"gdlr-heading-shortcode \"  style=\"color: #000000;font-size: 16px;font-weight: bold;\" >Program objectives<\/span><\/h3>\n<ul>\n<li>Train future researchers, professors and, more broadly, future data science stakeholders, primarily in the areas of expertise of IVADO members: operations research, machine learning and decision science.<\/li>\n<li>Promote the mobility, recruitment and retention of young researchers.<\/li>\n<li>Foster the development of collaborative and applied cutting-edge research.<\/li>\n<\/ul>\n<h3 class=\"gdlr-heading-shortcode \"  style=\"color: #000000;font-size: 16px;font-weight: bold;\" >Eligibility<\/h3>\n<p><span style=\"text-decoration: underline;\">Postdoctoral funding applicants must:<\/span><\/p>\n<ol>\n<li>Intend to attend <strong>HEC Montr\u00e9al, Polytechnique Montr\u00e9al, Universit\u00e9 de Montr\u00e9al, McGill University or University of Alberta<\/strong>;<\/li>\n<li>Have earned their first doctorate fewer than five years prior to the date on which they are applying or intend to earn their first doctorate by the date on which the competition results are announced (June, 2020). IVADO will be flexible with applicants who provide an adequate explanation for a career interruption or particular circumstances. This explanation must be included in the application (e.g. pregnancy\/maternity or sick leave);<\/li>\n<li>Priority will be given to candidates <strong>who have had their main PhD outside Quebec.<\/strong> This measure aims to promote the attraction of talented international researchers.<\/li>\n<\/ol>\n<p><span style=\"text-decoration: underline;\">Professor (supervisor) applicants must:<\/span><\/p>\n<ol>\n<li>Hold a faculty position as a professor at <strong>HEC Montr\u00e9al, Polytechnique Montr\u00e9al or Universit\u00e9 de Montr\u00e9al<\/strong>;<\/li>\n<li>Professors at the <strong>University of Alberta<\/strong> and <strong>McGill University<\/strong> may act as supervisors providing they are full members of at least one of IVADO research groups (Mila, CIRRELT, GERAD, CERC Data Science, CRM, Tech3Lab).<\/li>\n<li>Eligible professors are assistant professors, associate professors, full professors, research professors or visiting professors. Adjunct professors are not eligible.<\/li>\n<li>Not have acted as the applicant\u2019s PhD supervisor or co-supervisor;<\/li>\n<li><strong>Only submit one application to the competition.<\/strong><\/li>\n<li>Not supervise more than two postdoctoral researchers funded by this program (IVADO postdoctoral funding program) at the last possible start date for the funding (October 1, 2020).<\/li>\n<\/ol>\n<h3 class=\"gdlr-heading-shortcode \"  style=\"color: #000000;font-size: 16px;font-weight: bold;\" >Funding period<\/h3>\n<p>Start of the funding period: July 1st, October 1<sup style=\"text-transform:none;\">st<\/sup> 2020 or <span style=\"color: #ff0000;\">January 1st, 2021.<\/span><\/p>\n<h3 class=\"gdlr-heading-shortcode \"  style=\"color: #000000;font-size: 16px;font-weight: bold;\" >Amounts and terms <\/h3>\n<p>The funds (salary and reimbursement of relocation expenses) shall be transferred to the office of research of the supervisor\u2019s university, and the university shall pay the postdoctoral researcher according to its own compensation rules. For projects that require ethics approval, the funds shall only be paid out once the approval is granted. Some projects, including partnership projects, may require specific agreements (e.g. pertaining to intellectual property).<\/p>\n<p>Funding may be cut, withheld, delayed or rescinded under the circumstances outlined in the letter of award.<\/p>\n<h3 class=\"gdlr-heading-shortcode \"  style=\"color: #000000;font-size: 16px;font-weight: bold;\" >Competitive process <\/h3>\n<p><span style=\"text-decoration: underline;\"><strong>Review and criteria<\/strong><\/span><\/p>\n<p>The applications shall be reviewed to ensure compliance with program rules (e.g. applications that are incomplete, exceed the page limit or list an ineligible applicant or supervisor). Only the applications that meet all criteria will be forwarded to the review committee.<\/p>\n<p>The review committee shall be made up of professors well-readed in IVADO\u2019s areas of expertise and shall not be listed as a supervisor by any applicant. <span style=\"font-weight: 400;\">Depending on the availability of the reviewers, IVADO focuses on the constitution of a joint committee. G<\/span>iven the small size of the communities in certain areas, it may prove difficult to select expert reviewers who are not included in an application submitted to the competition. In such cases, a reviewer may be required to assess an application despite being listed in another application as a supervisor. An external reviewer may also join the committee. The committee shall ensure by all possible means that the reviewer does not influence the ranking of the application in which he\/she is included.<\/p>\n<p>The review committee shall then rank the applications based on <strong>excellence<\/strong>, as well as the project\u2019s <strong>alignment with IVADO\u2019s overarching framework<\/strong>, which aims to promote multidisciplinary collaboration and diversity in data science. In terms of excellence, the committee will specifically assess:<\/p>\n<ul>\n<li>the applicant\u2019s contributions to research (scientific impact, quality of research, productivity and previous funding)<br \/>\nthe quality of the applicant\u2019s doctoral thesis and his\/her academic excellence<\/li>\n<li>the extent and scope of the applicant\u2019s experience (multidisciplinary and professional experiences, extra-academic activities, collaborations, contributions to the scientific community and society as a whole, etc.)<\/li>\n<li>he alignment of the applicant\u2019s experience and proposed project<\/li>\n<\/ul>\n<p>Applicants who apply for partnership funding will also be ranked based on their projects\u2019 applied research potential.<\/p>\n<p>The review committee will rank the applicants seeking regular and partnership funding. While in session, the review committee may award a\u00a0<em>Fellow<\/em> funding to outstanding applicants seeking regular funding.<\/p>\n<p>Following a resolution of IVADO&#8217;s Scientific Committee, the review committee will not produce any comments on the evaluation.<\/p>\n<p><span style=\"text-decoration: underline;\"><strong>Final step and commitments<\/strong><\/span><\/p>\n<p>The postdoctoral researcher shall:<\/p>\n<ul>\n<li>be physically present at his\/her supervisor\u2019s university or share his\/her time between the home university and partner organization (for partnership funding);<\/li>\n<li>contribute to IVADO\u2019s community and activities by, for example, taking part in:\n<ul>\n<li>presentations on his\/her research;<\/li>\n<li>training and knowledge dissemination activities;<br \/>\nconsultations;<\/li>\n<li>activities generally undertaken by career researchers (mentorship, assessment, co-organization of events, etc.);<\/li>\n<\/ul>\n<\/li>\n<li>recognize that he\/she is a member of an academic community to which he\/she shall contribute;<\/li>\n<li>comply with the Tri-Agency Open Access Policy on Publication. Postdoctoral researchers are encouraged to publish their research findings (papers, recordings of presentations, source codes, databases, etc.), in compliance with the intellectual property rules that apply to their own specific case;<\/li>\n<li>recognize the financial support granted by IVADO and the CFREF or FRQ when disseminating the research results and, more broadly, in all the activities in which he\/she takes part<\/li>\n<\/ul>\n<p>The supervisor shall:<\/p>\n<ul>\n<li>provide a work environment that is conducive to the completion of the project<\/li>\n<li>oversee the work of the postdoctoral researcher<\/li>\n<\/ul>\n<\/div><div class=\"tab-content\" ><h3 class=\"gdlr-heading-shortcode \"  style=\"color: #00000;font-size: 16px;font-weight: bold;\" >FAQ<\/h3>\n<ul>\n<li>Is there a particular format for preparing a CV?\n<ul>\n<li>No, there is no particular format that needs to be followed.<\/li>\n<\/ul>\n<\/li>\n<li>Are there any specific rules for the recommendation letter?\n<ul>\n<li>No, there are no specific rules for the recommendation letter.<\/li>\n<\/ul>\n<\/li>\n<li><span style=\"font-weight: 400;\"> Can candidates download <\/span><span style=\"font-weight: 400;\">recommendation letters<\/span><span style=\"font-weight: 400;\"> themselves?<\/span>\n<ul>\n<li>\u00a0No, recommendation letters can be downloaded by the author of the letter.<\/li>\n<\/ul>\n<\/li>\n<li>Can I download my unofficial transcript?\n<ul>\n<li>No, you must send us your official transcript including all your current results. Originals or certified copies must be scanned and attached to the application and for non-Canadian universities, you must specify the rating scale.<\/li>\n<\/ul>\n<\/li>\n<li>I earned my PhD in a country that does not provide a transcript. What document(s) should I include instead?\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Please include a note in your application and provide the transcript for your master\u2019s degree.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<li>What are the conditions of the funding?\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>An example of the award lettrer <a href=\"https:\/\/vieux.ivado.ca\/wp-content\/uploads\/2020\/02\/2020_Lettre_octroi_postdoc-modalit\u00e9s.pdf\" target=\"_blank\" rel=\"noopener noreferrer\">is available here.<\/a><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<li>Can I have any other paid activity while receiving IVADO postdoctoral funding, such as consulting?\n<ul>\n<li>The amount of the funding is intended to allow the postdoctoral researcher to focus exclusively on his\/her research, but complementary activities are equally important to the postdoctoral researcher&#8217;s training. To balance these two aspects, it is acceptable to have paid activities:\n<ul>\n<li>that respect the policies of the home institution with respect to other sources of income.<\/li>\n<li>That do not prevent the trainee from doing the work for which he\/she is funded by IVADO as if he\/she were doing it full time.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<li>Can IVADO&#8217;s funding be combined with other funding?\n<ul>\n<li>IVADO postdoctoral funding cannot be held concurrently with other NSERC, SSHRC, CIHR or IVADO fundings. If you are successful in our competition and also in a competition from one of the organizations mentioned, you will have to choose one funding or the other, but not both.<\/li>\n<li>In general, we do not encourage the accumulation of fundings from other sources of funding, but we do not prohibit it either, as it may be justified in some cases.<\/li>\n<\/ul>\n<\/li>\n<li>Which professors are eligible to apply?\n<ul>\n<li>For the supervisor, the affiliation constraints are to be a professor:\n<ul>\n<li>Either at HEC Montr\u00e9al, Polytechnique Montr\u00e9al or the Universit\u00e9 de Montr\u00e9al, with no other constraints.<\/li>\n<li>Either at McGill University or the University of Alberta, but these professors must also be members of one of the following research groups: CIRRELT, GERAD, Mila or Canada Excellence Research Chair in Real-Time Decision Making, CRM, Tech3Lab.<\/li>\n<\/ul>\n<\/li>\n<li>For the supervisor, the eligible statuses are:\n<ul>\n<li>Assistant Professor, Associate Professor, Full Professor<\/li>\n<li>Research Professor<\/li>\n<li>Visiting professor<\/li>\n<\/ul>\n<\/li>\n<li>Adjunct professors are not eligible.<\/li>\n<li>A change in the status or affiliation of the supervisor during the course of the funding could lead to termination of the funding.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><strong>Partnership funding<\/strong><\/p>\n<ul>\n<li>Is it possible to apply for partnership funding without having a partner at the time of the application?\n<ul>\n<li>No, unfortunately, you need to find your partner before submitting your application. A letter of commitment from your partner is also required.<\/li>\n<\/ul>\n<\/li>\n<li><span style=\"font-weight: 400;\">For partnership funding, are there any specific rules for writing the confirmation letter from the partner and by whom should it be written?<\/span>\n<ul>\n<li>The confirmation letter must be written by the project supervisor and must contain the subject\/title of your project and the amount of their financial commitment ($ 35&nbsp;000\/year for two years).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>Didn\u2019t find what you were looking for? Send us an <a href=\"mailto:programmes-excellence@ivado.ca\">e-mail<\/a>.<\/p>\n<\/div><div class=\"tab-content\" ><p>Please apply through:\u00a0<a href=\"https:\/\/ivado.smapply.io\/\">https:\/\/ivado.smapply.io\/ <\/a>(Opening March 2nd, 2020).<\/p>\n<p>Applications sent by e-mail will not be accepted.<\/p>\n<p>All applications must submit:<\/p>\n<ul>\n<li>a questionnaire to be completed on the platform WITH a common-language description of the project (maximum length of one page);\n<ul>\n<li>an example of filled form\u00a0is available <a href=\"https:\/\/vieux.ivado.ca\/wp-content\/uploads\/2020\/03\/Postdoc2020_Formulaire-test_AN_3.pdf\" target=\"_blank\" rel=\"noopener noreferrer\">here<\/a>.<\/li>\n<\/ul>\n<\/li>\n<li>CV (free format)<\/li>\n<li>Ph.D transcripts (as well as information on the grading scale when the transcript is issued by a non-Canadian university)<\/li>\n<li>project description (maximum one page including references)<\/li>\n<li>recommendations (a minimum of two and a maximum of three), including a letter downloaded directly from the postdoctoral supervisor (or potential postdoctoral supervisor)<\/li>\n<li>confirmation from the partner (partnership funding applications only)<\/li>\n<\/ul>\n<\/div><div class=\"tab-content\" ><ul>\n<li><span data-sheets-value=\"{\" data-sheets-userformat=\"{\"><strong>Behrouz Babaki<\/strong> (Polytechnique Montr\u00e9al, Gilles Pesant)<\/span>\n<ul>\n<li>To turn the ever increasing amounts of data into social and economic value, two tasks need to be performed: 1) extracting knowledge from the data, and 2) incorporating this knowledge in the operations that drive the society. The machine learning community addresses the first task by extracting the knowledge from the data and capturing it into &#8216;learned models&#8217;. The second task is studied by the operations research community under the label of &#8216;optimization&#8217;. However, these techniques have been developed almost independently. This makes it less straightforward to integrate them and turn the knowledge obtained from a learned model into actionable decisions. In this project, we exploit the fundamental similarities between the two tasks to develop an integrated system that performs both tasks together. We apply our system to problems in business and finance and demonstrate how this approach can help players in these sectors to use their data for improving their operations.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Maxime Laborde<\/strong> (McGill, Adam Oberman)\n<ul>\n<li>This research is focused on using mathematical tools to accelerate the training time of Deep Neural Networks (DNN)s. DNNs are a powerful tool in Artificial Intelligence, behind applications in machine translation, image recognition, speech recognition and other areas. However training the DNNs requires huge computational resources, which is costly both financially, and in the human effort required to implement them. This research will use advanced mathematical tools to improve the time required to train DNNs.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tien Mai<\/strong> (<span data-sheets-value=\"{\" data-sheets-userformat=\"{\">Universit\u00e9 de Montr\u00e9al,\u00a0Teodor Gabriel Crainic)<\/span>\n<ul>\n<li>This project deals with the planning of intermodal rail transportation, integrating methodologies from operations research and machine learning in a new and innovative way. Intermodal container freight transportation is the backbone of international trade and supports a large part of Canadian and North-American imports and exports. Canada has one of the largest rail networks in the world and Canadian railway companies are both network and terminal operators. They face many large-scale optimization problems that are complex because of their sheer size and the uncertainty that affects planning and operations on a continuous basis. The project focuses on a tactical network load and block planning problem that involves decisions related to blocking and railcar fleet management. Assuming that the train schedule is given, the problem entails three consolidation processes: assignment of containers to railcars, of railcars to blocks and of blocks to trains. The project will be dedicated to designing a service network design model and associated solution method that allows to solve realistic, large scale, instances.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Abbas Mehrabian<\/strong> (McGill,\u00a0Luc Devroye)\n<ul>\n<li>When designing a machine learning algorithm, it is crucial for the designer to understand the input data to which this algorithm will be applied. It is well known that real-world data for any task has a lot of structure, exploiting which allows for faster learning and more accurate prediction. However, understanding this structure is a highly nontrivial task, given the high dimension of the data. In this project we propose to develop a mathematical framework for learning the structure hidden in the data, via the lens of probability theory. Assuming the data is generated by some stochastic process, we would like to infer its distributional properties. Then a natural question is, which distributions are harder to learn, and which ones are easier. The aim of this project is to answer this question from statistical and computational perspectives, at least for a variety of commonly used classes of distributions, such as mixture models and graphical models.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Patrick Munroe<\/strong> (Polytechnique Montr\u00e9al,\u00a0Fran\u00e7ois Soumis)\n<ul>\n<li>Gestion en temps r\u00e9el du cargo a\u00e9rien. Le projet \u00e0 moyen terme est le d\u00e9veloppement d&#8217;un syst\u00e8me de gestion du cargo dans les compagnies a\u00e9riennes en commen\u00e7ant avec Air Canada. Ce syst\u00e8me traitera la planification strat\u00e9gique, tactique et l&#8217;op\u00e9ration en temps-r\u00e9el. Le niveau strat\u00e9gique \u00e9value des sc\u00e9narios \u00e0 long terme sur l&#8217;organisation du r\u00e9seau, les march\u00e9s \u00e0 d\u00e9velopper, les alliances \u00e0 conclure. Le niveau tactique optimise le choix des itin\u00e9raires entre chaque paire de villes pour une semaine type d&#8217;une saison. Durant l&#8217;op\u00e9ration, les vendeurs pourront obtenir en ligne le meilleur itin\u00e9raire pour acheminer une nouvelle commande et le prix de revient. \u00c0 chaque niveau de d\u00e9cision, il faut estimer la demande pour l&#8217;horizon consid\u00e9r\u00e9 et optimiser l&#8217;acheminement de cette demande dans le r\u00e9seau de transport comprenant des avions tout cargo, l&#8217;espace disponible dans les soutes des vols passagers, des sous-contrats avec d&#8217;autres transporteurs a\u00e9riens et routiers. La recherche portera sur le d\u00e9veloppement de nouvelles m\u00e9thodes d\u2019estimation de la demande et d&#8217;optimisation de l&#8217;acheminement dans un grand r\u00e9seau.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Maria Isabel Restrepo Ruiz<\/strong> (Polytechnique Montr\u00e9al,\u00a0Nadia Lahrichi)\n<ul>\n<li>The main objective in using optimization approaches for demand and supply management in home healthcare is to match supply and demand by influencing patients\/caregivers choices for service time slots\/working shifts. Our aim with this project is to develop a decision support tool to deal with approaches for demand and supply management in home healthcare. Specifically, we will implement stochastic models to forecast future demands and to predict caregivers&#8217; absenteeism. Then, we will design and develop choice models to consider patient and caregiver choice behavior. These models will predict the probability of choosing a particular alternative from an offered set (e.g. visit time slots, working shifts) given historical choice data about an individual or a segment of similar individuals. These models will be embedded into an optimization approach that will compute a time slotting\/scheduling plan or a pricing strategy to optimally balance the allocation of cost-effective schedules to caregivers and the improvement of service quality.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Anne-Lise Saive<\/strong> (Universit\u00e9 de Montr\u00e9al,\u00a0Karim Jerbi)\n<ul>\n<li>Every day, we experience thousands of situations, but we only remember few of them. Episodic memory is the only memory system that allows people to consciously re-experience past experiences and it is the most sensitive to age and neurodegenerative diseases. It is thus critical to better understand how to enhance learning and memory in both healthy and clinical populations. Emotions are known to robustly strengthen the formation of long-term memories. Characterizing the influence of positive emotions (joy, happiness) on memory could be pivotal in improving memory therapies, yet the underlying brain mechanisms are still surprisingly misunderstood. In this project, we will use a fully data-driven approach to identify the key neuronal processes strengthened by positive emotions that distinguish events we will durably remember from events we will forget. We will combine for the first time high spatial and temporal resolution brain imaging techniques and state-of-the-art machine-learning algorithms. This will be achieved by assessing the ability of multidimensional (across space, time and frequency) arrays of brain data to predict future memory accuracy.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Rabih Salhab<\/strong> (HEC Montr\u00e9al,\u00a0Georges Zaccour)\n<ul>\n<li>Ride-sharing services such as Uber, Lyft or Didi Chuxing match a group of drivers providing rides with customers through an online ride-sharing platform. This business model faces a number of fundamental challenges. Indeed, the drivers considered as independent contractors choose the area they wish to serve, if they accept or reject rides, and when they start and stop working. With no direct control over the drivers, the ride-sharing platform can only use incentives and select the information it provides to drivers and customers in order to improve the quality of service and balance supply and demand. This project aims to develop a model that anticipates how the drivers respond to provided information, which is a combination of request statistics, prices at various locations and times, and estimation of the state of the road network. Moreover, it intends to generate location and time-dependent pricing schemes and optimal information filters in order to optimize the efficiency of the system. For example, the filters control the amount of information to release to drivers about the requests in order to balance the supply and demand and avoid the drivers from deserting some areas.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Kristen Schell<\/strong> (Polytechnique Montr\u00e9al,\u00a0Miguel Anjos)\n<ul>\n<li>Hydro-Qu\u00e9bec is geographically well positioned to make significant profits in neighboring electricity markets. Facing political mandates to retire coal and nuclear power plants, the markets of Ontario, New York and New England are under increasing stress to provide stable, baseload electricity production. We will utilize the vast historical data from these markets to model their future evolution. Using the insights obtained from this analysis, we will be able to determine optimal strategies for Hydro-Qu\u00e9bec to maximize its profits through targeted investment decisions in market interconnections. The results will be generalizable to other provincial utilities in Canada and their participation in the relevant electricity markets.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Jean-Fran\u00e7ois Spinella<\/strong> (Universit\u00e9 de Montr\u00e9al,\u00a0Guy Sauvageau)\n<ul>\n<li>Acute myeloid leukemia (AML) is the most common form of leukemia in adults. Despite advances in supportive care to treat therapy-related complications, the majority of AML patients will not exceed the two-year survival mark because of relapse. This dismal outcome reflects the sub-optimal treatment orientation of poorly understood subtypes of AML. To improve the treatment and outcome of patients, Dr. Guy Sauvageau and colleagues initiated in 2009 the Leucegene project which has become an internationally acknowledged leader in genetic and biological characterization of AML. Exploiting the most innovative technologies, this program already allowed the sequencing of 452 primary human AML specimens. While several types of genomic alterations have been explored in AML, some of them, such as modifications to the chromosome structure, remain elusive despite their known importance in cancer. We are convinced that this is due to unsuitable analysis and we propose here an innovative machine learning approach to efficiently identify these modifications. Tests will be carried out on our sequenced AML specimens. Ultimately, the method will be released to help the scientific community to exploit its cancer data. From a biomedical point of view, it will allow for better definition of AML subgroups, as well as an increase in the chances of identifying new markers for this disease. With the goal to accelerate the transfer of new knowledge from the laboratory to the bedside, this project will help ensure the correct classification and treatment of AML.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Yu Zhang<\/strong> (Universit\u00e9 de Montr\u00e9al,\u00a0Pierre Bellec)\n<ul>\n<li>To understand brain mechanism of cognitive functions is the ultimate goal of neuroscience studies, which also provides fundamental guidance for developing new techniques in artificial intelligence. With accumulated evidence in animals and humans, functional dynamics is suggested to be the non-stationary nature of cognitive process. In this project, we aim to apply deep learning models to characterize the spatial and temporal dynamics of BOLD signals at rest and during cognitive tasks. To account for the temporal dependence of MRI signals, a convolutional recurrent neural network is first used to characterize the spatial and temporal dynamics of resting-state data, and then to map the dynamic somatotopic maps during movement of tongue, hand and foot. The model is further adjusted for classification of functional dynamics among multiple task conditions. The derived characteristic functional dynamics, including sequential temporal response functions and corresponding activation patterns, reveals the dynamic process of human cognitive function and provides essential guidance for brain simulation. Furthermore, our proposed method could also be used in clinic applications, for instance searching for temporal and spatial biomarkers for Alzheimer&#8217;s disease and evaluating the treatment effects of precision medicine.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/div><div class=\"tab-content\" ><ul>\n<li><strong>Jonathan Binas\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al, Yoshua Bengio)\n<ul>\n<li>Recent machine learning approaches have led to impressive demonstrations of machines solving a great variety of difficult tasks, which previously were thought to be restricted to humans. Applied to areas such as health care, environmental challenges, optimization of transport and logistics, or industrial processes, these advances will lead to improved living conditions and the creation of value. While being loosely inspired by biological neural systems, artificial neural networks starkly differ from their biological counterparts in almost every respect. In particular,<br \/>\nbrains can learn from very few examples, infer causal relationships, and seamlessly transfer skills to new tasks, whereas current machine learning models require enormous amounts of data to just master a single task. To overcome some of these limitations, we introduce new, brain-inspired models for learning and memory, which will allow for meaningful information to be extracted from data more efficiently. The resulting systems will lead to improved, more powerful machine learning systems, which can be applied in numerous contexts, including medical applications, automation, robotics, or forecasting.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Marco Bonizzato\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al, Marina Martinez)\n<ul>\n<li>A quarter million people every year are affected by spinal cord injury (SCI), which causes paraplegia. When the lesion is incomplete some recovery can occur. Spinal cord stimulation can be applied to help people with SCI to regain control of the paralyzed legs. In the last year Prof. Martinez and I demonstrated a new neuroprosthetic concept whereby cortical stimulation is applied to improve walking. This novel strategy empowers the brain&#8217;s own residual networks and increases voluntary control of leg movement with long lasting beneficial effects for recovery. &#8220;Fire together, wire together&#8221; is the established rule for neural repair. Here we propose to combine for the first time brain and spinal stimulation into an unique combined neuroprosthesis. This approach is compelling, but complicated by the overwhelming amount of stimulation parameters that needs to be characterized. We propose to solve this problem with machine learning. The first ever intelligent neuroprosthesis will monitor changes in muscular activity to explore and learn an optimal set of stimulation parameters. Our results can be rapidly translated to clinical tests.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Elie Bou Assi\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0Dang K. Nguyen)\n<ul>\n<li>Epilepsy is a chronic neurological condition that affects as many as 1 in every 100 Canadians. While first line of treatment consists of long-term drug therapy more than a third of patients suffer from seizures that are resistant to antiepileptic drugs. Due to their unpredictable nature, uncontrolled seizures represent a major personal handicap and source of worriment for patients. In addition, persistent seizures constitute a considerable public health burden due to high use of health care resources, high number of disability days or unemployment, and low annual income. Some of the difficulties and challenges faced by drug-refractory patients can be overpassed by implementing algorithms able to anticipate seizures. With accurate seizure forecasting, one could ameliorate refractory epilepsy management improving social integration, productivity and quality of life. Our main objective is the development of a real-time seizure prediction system, based on deep learning, intended to warn patients or caretakers about an incoming seizure and recommend advisory measures.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Quentin Cappart\u00a0<\/strong>(Polytechnique Montr\u00e9al,\u00a0Louis-Martin Rousseau)\n<ul>\n<li>L\u2019optimisation combinatoire occupe une place pr\u00e9pond\u00e9rante dans notre soci\u00e9t\u00e9 actuelle. Que ce soit la logistique, le transport ou la gestion financi\u00e8re, tous ses domaines se retrouvent confront\u00e9s \u00e0 des probl\u00e8mes pour lesquels on recherche la meilleure solution. Cependant, un grand nombre de probl\u00e8mes tr\u00e8s complexes reste encore hors de port\u00e9e des m\u00e9thodes d\u2019optimisation actuelles. C\u2019est pourquoi, l\u2019am\u00e9lioration de ces techniques est un sujet crucial. Parmi ces derni\u00e8res, les diagrammes de d\u00e9cisions semblent avoir un avenir prometteur. Un diagramme de d\u00e9cision est une structure qui permet de repre\u0301senter de manie\u0300re compacte un proble\u0300me tout en pre\u0301servant ses caract\u00e9ristiques. Cependant, leur efficacit\u00e9 est extr\u00eamement d\u00e9pendante de l\u2019ordre des variables utilis\u00e9 pour leur construction. L\u2019objectif de ce projet est d\u2019utiliser les m\u00e9thodes r\u00e9centes d\u2019apprentissage automatique pour ordonner les variables lors de la construction d&#8217;un diagramme de d\u00e9cision. Les contributions de ce projet permettront la r\u00e9solution de probl\u00e8mes combinatoires plus complexes, et plus larges que ce que peuvent faire les m\u00e9thodes de l&#8217;\u00e9tat de l&#8217;art. Nous nous consacrerons principalement aux probl\u00e8mes r\u00e9els li\u00e9s au transport et \u00e0 la logistique. Ce projet sera effectu\u00e9 en partenariat avec l&#8217;entreprise Element-AI.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Jasmin Coulombe-Huntington\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0Micheal Tyers)\n<ul>\n<li>Drug combinations can simultaneously target redundant biological pathways and thus offer unique advantages for disease treatment. By growing human cancer cells each with a specific gene deletion in the presence of a drug, we identified gene deletions which make cells more sensitive or more resistant to the growth-inhibition effects of &gt;230 different drugs. In this proposal, I outline a plan to develop software tools to exploit this resource in order to precisely characterize drug mechanisms and to predict useful drug combinations. Tumor growth relies on overactive biomass and energy production, and I found that close to 80% of the drugs we screened altered the sensitivity of cells to the deletion of metabolic genes. I will use a genome-scale mathematical model of cell metabolism to attribute these effects to the lowered activity of other metabolic genes, those whose activities we predict are directly affected by the drug. After modelling the effects of each drug on cell metabolism, we will simulate the effects of drug combinations to identify pairs which effectively block the generation of small molecules important to tumor growth.available data on the effectiveness of drug combinations, I will train a machine learning algorithm to use similar gene deletion data as well as drug molecular similarities to predict useful drug combinations for the treatment of cancer and potentially other diseases. I will also attempt to predict the direct molecular targets of each drug by modelling molecular signalling in cells, leveraging known signalling pathways, molecular interaction networks and pairs of gene deletions sensitive or resistant to similar sets of drugs.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Pouria Dasmeh\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0Adrian Serohijos)\n<ul>\n<li>The rise of antibiotic resistance has put antimicrobials, once believed to be miracles of modern medicine, into jeopardy1. The current death toll of AMR is ~800,000 per year (i.e., ~100 per hour) and is expected to rise to ~ 16 million in 2050. In Canada alone, the financial burden of antibiotic resistance is ~&nbsp;$200 million annually. A key knowledge in our battle against antibiotic resistance is to predict the growth rate of bacteria at different concentrations of antibiotics. Recently, the response of bacterial strains to antibiotics were measured for all possible mutations in important enzymes that confer resistance to beta-lactam antibiotics (e.g., penicillins, ampicillins, etc.). In this project, I will employ the power of machine learning to develop predictive models of resistance at different antibiotic dosages from the available large-scale datasets. This approach would have immediate impacts on the design of antibiotic dosages that prevent or delay the onset of resistance. In this integration of machine learning with biochemistry and molecular medicine, we will seek the potentials of data science to aid decision-making in medicine.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Benoit Delcroix\u00a0<\/strong>(Polytechnique Montr\u00e9al,\u00a0Michel Bernier)\n<ul>\n<li>Un d\u00e9fi majeur dans le secteur du b\u00e2timent est l\u2019&#8217;absence de syst\u00e8mes continus de suivi de la performance et d&#8217;\u00e9valuation des \u00e9carts de performance entre la situation observ\u00e9e et celle d\u00e9sir\u00e9e. L&#8217;op\u00e9ration non-optimale des syst\u00e8mes de Chauffage, Ventilation et Conditionnement d\u2019Air (CVCA) entra\u00eene des pertes \u00e9nerg\u00e9tiques et de confort des occupants. Le secteur du b\u00e2timent repr\u00e9sente environ un tiers de la consommation \u00e9nerg\u00e9tique au Qu\u00e9bec et au Canada. Ainsi, des mesures d\u2019&#8217;efficacit\u00e9 dans ce secteur produisent des impacts positifs majeurs. L&#8217;id\u00e9e de ce projet est d&#8217;utiliser des m\u00e9thodes d&#8217;apprentissage profond pour exploiter les larges jeux de donn\u00e9es g\u00e9n\u00e9r\u00e9s par les syst\u00e8mes CVCA. Le but final est d&#8217;automatiser la d\u00e9tection et le diagnostic des anomalies, et d&#8217;optimiser l&#8217;op\u00e9ration des \u00e9quipements. Les b\u00e9n\u00e9fices incluent une gestion am\u00e9lior\u00e9e de l&#8217;\u00e9nergie et une meilleure prise en compte du confort des occupants. Au terme de ce projet, des outils de d\u00e9tection \/ diagnostic \/ contr\u00f4le bas\u00e9s sur l&#8217;apprentissage profond seront d\u00e9velopp\u00e9s et test\u00e9s \u00e0 des fins d&#8217;implantation dans des b\u00e2timents r\u00e9els.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Golnoosh Farnadi\u00a0<\/strong>(Polytechnique Montr\u00e9al,\u00a0Michel Gendreau)\n<ul>\n<li>The increasing use of algorithmic decision-making in domains that affect people\u2019s lives, has raised concerns about possible biases and discrimination that such systems might introduce. Recent concerns on algorithmic discrimination have motivated the development of fairness-aware mechanisms in the machine learning (ML) community and the operations research (OR) community, independently. While in fairness-aware ML, the focus is usually on ensuring that the inference and predictions produced by a learned model are fair, the OR community has developed methods to ensure fairness in solutions of an optimization problem. In this project, I plan to build on the complementary strengths of fairness methods in ML and OR to address these shortcomings in a fair data-driven decision-making system. I will apply this work to real-world problems in the areas of personalized education, employment hiring (business), social well-being (health), and network design (transportation). The advantage of my proposed system compared to the existing works is that it: 1) incorporates domain knowledge with data-driven probabilistic models, 2) detects and describes complex discriminative patterns, 3) returns a fair decision\/policy, and 4) breaks negative\/positive feedback loops.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Kuldeep Kumar\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0S\u00e9bastien Jacquemont)\n<ul>\n<li>Neurodevelopmental disorders (NDs) including intellectual disabilities (ID), severe learning disabilities, and autism spectrum disorder (ASD) represent a significant health-care burden. The genetic contribution to NDs ranges from 50 to 80%. However, the interpretation of genetic mutations in the neurodevelopmental clinic remains, in many cases, a rough approximation. Over 3,500 whole genome chromosomal microarrays (CMAs) are performed yearly at the CHU-SJ, and for more than 95% of the mutations reported to patients, the effects on cognitive traits and brain function are unknown. With the development of the clinical exome, the proportion of undocumented rare mutations will continue to increase. To fill the widening gap between genome technologies and clinical neurosciences, we propose a ground-breaking strategy to accurately model the effects of copy-number-variations (CNVs), genome-wide, on cognition, brain structure and function. Towards this goal, recent machine learning techniques related to manifold approximation and deep learning will be investigated to learn a latent representation for multi-subject data that considers multi-modal information. In a large-scale analysis with over 20,000 individuals, multi-variate copy-number-variation (CNV) association analysis will assess the contribution of structure\/function MRI modalities to rare genomic psychiatric risk factors. The deliverables of our project are models that can predict the effect of any rare mutation on cognition, brain structure and connectivity. This will allow clinicians to quantify the contribution of genetic variants to the neurodevelopmental symptoms of their patient.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Elizaveta Kuznetsova\u00a0<\/strong>(Polytechnique Montr\u00e9al,\u00a0Miguel Anjos)\n<ul>\n<li>The cumulative solar and wind power capacity integrated mainly into low and medium voltage grids in Canada represents 9% of total available power capacity in 2015, and is expected to more than double by 2040. This reality will create not only opportunities for sustainable energy production, but also challenges for the system operator due to the uncertain power fluctuations from supporting multiple prosumers (customers who can alternatively behave as energy consumers or producers). This project addresses the question of how to involve prosumers in the energy management process for provision of ancillary services in the grid (e.g. voltage control) while mitigating unsuitable emerging effects. The idea is to consider a three-layer optimization problem related to different voltage levels (high, medium and low). Grid incentives will be optimized at the high voltage level, while lower levels will optimize the dispatch among grid prosumers to maximize their involvement. An Agent-Based Modelling framework will provide a backbone for this multi-level optimization, enable bi-directional information flows, and make it possible to handle the challenges of high data volume and complexity.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tarek Lajnef\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0Karim Jerbi)\n<ul>\n<li>Our fast-paced performance-oriented modern societies have led to a serge in stress, anxiety and depression with severe impacts on sleep and the overall quality of life. Additionally, alterations in sleep also occur as a natural consequence of healthy aging and vary as a function of gender. Here we propose to apply state-of-art machine learning tools to brain data from large cohorts (14.000 individuals) in order to improve our understanding of the effect of aging and mood on patterns of brain activity assessed during sleep. We will apply multivariate machine learning techniques for classification and regression using a wide range of behavioural and electroencephalographic features in order to investigate the link between brain activity patterns observable during sleep and behavioural measures of anxiety\/depression\/stress. By exploring these links across the lifespan and as a function of gender, this research will pave the way for the development of novel diagnostic\/therapeutic approaches.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Neda Navidi\u00a0<\/strong>(Polytechnique Montr\u00e9al,\u00a0Nicolas Saunier)\n<ul>\n<li>Learning driving behavior from smartphone location and motion sensors Monitoring and tracking vehicles and driving behavior are of great interest to better assess safety and understand the relationship with potential factors related to the infrastructure, vehicles and users. This has been implemented in recent years by car insurance to better assess their customers\u2019 risk of crash and offer usage-based premium. Driver monitoring and analysis or driver behavior profiling is the process of automatically collecting driving data (e.g., location, speed, acceleration) and predicting the crash risk. These systems are mainly based on Global Positioning System (GPS), which suffers from accuracy issues, e.g. in urban canyons, and is insufficient to detect normal and risky driving events like steering and braking to assess the driving behaviours. To address this problem, researchers have proposed the integration of GPS, Inertial Navigation System (INS) and motion sensors, and map-matching (MM) in a single hybrid system. INS is fused with GPS and used during signal outages to provide continuous positioning (dead reckoning). Map matching is the process of estimating a user&#8217;s position on a road segment, which provides more contextual information like road geometry and conditions, historical risk of the segment and other drivers&#8217; behaviour. The objective of this work is to improve the understanding of driver behaviour and crash risk by integrating location and motion data, driving events and road attributes using different machine learning algorithms.The objective of this work is to improve the understanding of driver behaviour and crash risk by integrating location and motion data, driving events and road attributes. The specific objectives are the following: 1) to detect risky driving events, namely hard acceleration\/braking, compliance to signalization (e.g. speed limits), sharp steering, tailgating, improper passing and weaving from location and motion data using machine learning (ML); 2) to apply map-matching algorithms to extract road-related attributes; 3) to cluster driver behaviour based on the time series of location and motion data, detected driving events and road-related attributes.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Nurit Oliker\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0Bernard Gendron)\n<ul>\n<li>We study the context of a transportation network manager who wants to take decisions on infrastructures, assets and resources to deploy in order to achieve its objectives. The network manager has to take into account that there are several classes of users, most of which pursue their own objectives within the rules stated by the manager, while others have objectives that are antagonist to those of the manager. Our goal is to develop methodology to help the transportation network manager. The application that motivates this research project is based on the transportation network design problem faced by a vehicle inspection agency who wants to inspect a maximum number of vehicles on a given territory under a limited budget. In such application, it is important to take into account the fact that some users will react to the installation of new vehicle inspection stations by diverting from their usual path to avoid inspection. Other applications of interest include the design of transportation networks that are resilient to major accidents and terrorist attacks. In this context, the network manager must anticipate potential threats posed by hostile users.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Camilo Ortiz Astorquiza\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0Emma Frejinger)\n<ul>\n<li>The railway industry represents one of the most important means of freight transportation. In Canada only more than 900,000 tons of goods are moved every day. where one of the major companies of the sector is Canadian National Railways (CN). An important component in their overall structure is the locomotive fleet management. The high cost of each locomotive and the large number of them required to satisfy train schedules makes the locomotive planning highly valuable. This in turn, represents an environmental and macroeconomic effect of great importance. Although several variants of locomotive planning problems have been studied before there is still a huge gap between the state-of-practice and the state-of-the-art. Thus, we will first study an optimization model that is tailored for CN&#8217;s requirements. Moreover, we will investigate on the development of specialized solution methods that incorporate machine learning with operations research techniques to obtain optimal solutions within reasonable time. This will provide a tool for the partner company to better evaluate scenarios in the locomotive planning and give value to the data while representing an important scientific contribution for the optimization community.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Musa Ozboyaci\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0Sebastian Pechmann)\n<ul>\n<li>Protein homeostasis describes the cells capability to keep its proteins in their correct shape and function through a complex regulatory system that integrates protein synthesis, folding and degradation. How cells maintain protein homeostasis is a fundamental phenomenon, an understanding of which has direct implications for prevention and treatment of severe human diseases such as Alzheimer\u2019s and Parkinson\u2019s. The protein quality control is regulated through specific enzymes called molecular chaperones that assist the (re)folding of proteins thus managing a complex and varied proteome efficiently. Although the specificity of interactions of these chaperones with their client proteins is known to be the key to the efficient allocation of protein quality control capacity, a significant yet unanswered question lies in rationalizing the principles of this specificity. This project aims to systematically define the principles of sequence specificity across eukaryotic chaperone network through a combination of molecular modelling and machine learning methods. To this end, the peptide sequences that confer chaperone specificity will be identified systematically using a robust docking procedure accelerated by a Random Forest model. To account for the conditional interdependencies of the energetic contributions of the peptide residues binding to the chaperone receptor and to capture them, probabilistic graphical models will be developed and deep learning methods will be applied to the large dataset obtained from docking simulations. This project, through the unique and rich dataset we will construct and the sophisticated analyses we will apply, will not only unravel the sequence specificity in protein homeostasis interactions during health and disease, but also provide the necessary guidelines for how it can be re-engineered for rational therapeutic intervention.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Maximilian Puelma Touzel\u00a0<\/strong>(Universit\u00e9 de Montr\u00e9al,\u00a0Guillaume Lajoie)\n<ul>\n<li>Recurrent neural nets are neuroscience-inspired AI algorithms that are revolutionizing the machine learning of complex sequences. They help power a variety of widely used applications such as Google Translate and Apple\u2019&#8217;s Siri. But they are also big, complicated models, and learning them is a delicate process, up to now requiring much fine-tuning to avoid the parameter adjustments getting out of control. The human brain also faces this stability problem when it learns sequences, but it has a robust, working solution that we are only beginning to understand. Bringing together experts in neuroscience, applied math, and artificial intelligence, we will adapt sophisticated methods for measuring stability from the mathematics of dynamical systems. We will develop learning algorithms that use this information to efficiently guide the learning, and will employ them in a neuroscience study that compares artificial and brain solutions to learning complex task sequences. Our goal is to unify and extend our understanding of how natural and artificial recurrent neural nets learn complex sequences.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Raphael Harry Frederico Ribeiro Kramer\u00a0<\/strong>(Polytechnique Montr\u00e9al,\u00a0Guy Desaulniers)\n<ul>\n<li>Facility location arises as an important field in combinatorial optimization with applications to logistics and data mining. In facility location problems (FLPs), one seeks to find the location of some supply points and to assign customers to those supply points so as to optimize a certain measure of performance. In data mining, several FLPs can be used with the purpose of modelling and solving clustering problems. The p-center problem (PCP) is an example of such type of problem, in which one seeks to find the location of p points (namely the centers) so as to minimize the maximum dissimilarity between any customer and its closest center. This problem is extremely difficult in practice. In a recent article co-authored by the candidate, the most classical variant of the PCP (namely the vertex PCP) is solved by an iterative algorithm for problems containing up to a million data points within reasonable time limits. This is more than 200x larger than previous algorithms. In this project we aim at extending some of the ideas used in that article to solve other classes of facility location problems for large datasets.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Joshua Stipancic\u00a0<\/strong>(HEC Montr\u00e9al,\u00a0Aur\u00e9lie Labbe)\n<ul>\n<li>Road traffic crashes are a serious concern. Typically, dangerous locations in the road network are identified based on historical crash data. However, using crashes is not ideal, as crash data bases contain error and omissions and crashes are not perfect predictors of safety. Our earlier work demonstrates how mobile sensor data, such as GPS travel data collected from regular drivers, can be used to substitute crash data in the safety management process within Quebec City. However, advanced statistical models must be developed to convert the collected sensor data into predicted crash counts at sites throughout the network. This project proposes three advancements to crash models developed in previous work. First, methods for imputing missing data will be proposed and explored. The effect of these methods on the final predicted crash counts will also be quantified. Second, techniques for expanding analysis to an entire road network will be developed. Third, the developed models will be tested on additional datasets in Montreal and Toronto. The ability to predict levels of safety with mobile sensor data is a substantial contribution to the field of transportation.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/div><div class=\"tab-content\" ><ul>\n<li><strong>Eugene Belilovsky<\/strong> (Aaron Courville, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>Towards Learning Language Based Navigation in Visually Rich 3-D Environments<\/li>\n<li>A long term goal of artificial intelligence and robotics is a robot able to perform manual tasks by understanding language instructions or questions and using visual and other sensory input to navigate and interact in a complex environment to achieve it\u2019s goals. Advances in machine learning have succeeded in important perceptual sub-tasks of this problem: object recognition, speech recognition, natural language processing among others. However, how to integrate these successes with sequential decision making and multi-modal reasoning across language, vision, and other modalities is an open question that has been difficult to study. Very recently visually rich 3-D simulations and tasks have arisen aimed to allow the development of algorithms for learning language directed navigation of robots. Even in these constrained simulations, straightforward application of existing machine learning and reinforcement learning techniques are unable to effectively tackle this new set of challenges. We aim to develop methods for these problems focusing on visual relational reasoning and ideas from human learning. We also strive to advance the nascent evaluation methodology of these algorithms. Besides making steps towards our ambitions of creating intelligent agents, methods developed to solve these tasks can be directly applied in household automation, robotic assistants, manufacturing, and autonomous driving.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Glen Berseth<\/strong> (Christopher Pal, Polytechnique Montr\u00e9al)\n<ul>\n<li>Visual Imitation Learning With Partial Information<\/li>\n<li>For many control and decision-making tasks, it is complex to describe the desired behaviour we hope to elicit from a robot. Many complex tasks that we want robots to be able to perform are dependant on a skill that people acquire at a young age, imitation. The ability of animals to learn from demonstrations has triggered research across many disciplines. This work will push the possibilities of imitation learning by creating methods that will allow robots to learn from diverse video demonstration. Of particular interest are skills that involve interaction with objects in the real world. Imitation learning is a tough problem but is also a very important one. If we make enough progress on imitation learning average people could program robots by providing a few demonstrations of the desired task in the real world.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Jhelum Chakravorty<\/strong> (Doina Precup, McGill University)\n<ul>\n<li>Temporal abstraction in multi-agent environment<\/li>\n<li>Temporal abstraction refers to the ability of an intelligent agent to reason, act and plan at multiple time scales. The question of how to obtain and reason with temporally abstract representations has been extensively studied in classical planning and control theory, and more recently it has become an important topic in reinforcement learning, especially through the framework of options. The theoretical development of options is based on the framework of Semi-Markov Decision Processes (SMDPs), in which an agent interacts with its environment by observing states and taking actions. As a result of an action, the agent receives an immediate reward, and transitions to a new state drawn from some distribution, after a certain period of time which is also drawn stochastically. Both the state and the dwell-time distribution are dependent only on the agent&#8217;s state and action. However, in many cases of practical importance, an agent may be faced either with more general environments, in which the environment may be partially observable, or there may be multiple agents acting in the environment. For example, in energy markets or in transportation there may be many agents, who would be interacting with each other and making decisions without being able to observe relevant information except at specific time points.We propose to focus on establishing a mathematical framework for temporal abstraction which would work in Decentralized Partially Observable Markov Decision Processes. In a multi-agent system, agents take decision and exchange their information at designated decision epochs. In general, the decision epochs are given by the realizations of a random sequence. Instead of looking at every instant of time, when an action is taken by an agent, we are interested in the Decentralized Semi-Markov Decision Processes (Dec-SMDPs), in which a Partially Observable Markov Decision Process (POMDP) corresponding to an agent is embedded between any two successive decision epochs. In between two such decision epochs, each agent chooses actions so as to maximize the total return over a finite or infinite horizon, i.e., it solves a POMDP problem. The optimal decision epochs are chosen based on a given criterion, e.g., exchanging information at some goal states fixed a priori or when the increase of reward from the last decision epoch is less than a threshold. The overall performance, which is to be maximized through such sequential decision making consists of two rewards. The exchange of information in encouraged by an extrinsic reward along with an intrinsic reward that is maximized in between two consecutive decision epochs.We would like to investigate two aspects of this problem setup. First, we are interested in formally establishing the framework for Partially Observable Semi-Markov Decision Processes and its extension to decentralized (multi-agent) problems. We would like to investigate if under certain simplifying assumptions in the planning problem, the posterior beliefs (i.e., belief on the state of the environment based on past information and current action) exhibit certain monotonicity and symmetry properties so that we can infer what the structure of optimal policies could be. We also want to establish the general Dec-SMDP framework for modeling this problem and characterize its properties in comparison with SMDPs.In the subsequent analysis, we would like to investigate learning algorithms for these families of problems. We will build on standard reinforcement learning algorithms for temporal abstraction, such as option-critic, and provide extensions in our case that are consistent with the theoretical characterization of these problems. We will also examine the performance of both value-function-based and policy-gradient style algorithms in this context. We will compare the results that can be obtained using our framework to results in which each agent ignores the others and only tries to optimize myopically its own reward. We will use both standard simulated small problems from the multi-agent literature, designed to emphasize specific aspects, as well as larger scale domains that correspond to simulate transportation and energy markets, where multiple agents work in a cooperative setting to achieve a common task in a decentralized manner, e.g., self-driving cars and smart-grids. In such applications the agents occasionally communicate among themselves and use a common information to update a belief about the state of the world and a local information to decide about their individual policies and terminations of such policies.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Ricardo de Azambuja<\/strong> (Giovanni Beltrame, Polytechnique Montr\u00e9al)\n<ul>\n<li>High Fidelity Data Collection for Precision Agriculture with Drone Swarms<\/li>\n<li>Projections from United Nations show that by 2050 we will need to produce 70% more food. However, agriculture already takes over 38% of the land and it is the largest user of freshwater in the world. What can we do to improve the way food is produced? We propose high precision agriculture! It uses big data to support decisions increasing productivity and reducing the use of land, water, fertilizers, pesticides, herbicides and fungicides. The use of more intelligent methods is also beneficial to biodiversity, changing the way natural resources are managed from an one-size-fits-all approach to a tailor-made solution. Yet, traditional data sources are known to have limited resolution and even low altitude remote sensing (e.g. airplanes or unmanned aerial vehicles &#8211; UAVs) can only see from a fixed perspective: above. Additionally, according to PwC there&#8217;s a&nbsp;$32.4bn market for UAVs in the agriculture industry. This project proposes to improve productivity and sustainability by increasing the precision of the data collected down to the individual plant level with the use of Artificial Intelligence (Deep Convolutional Neural Networks) powered autonomous micro aerial vehicle swarms capable to fly among crops (e.g. corn, soybean and oats). With the high resolution data collected by a swarm of small and cost effective drones, farmers will be able to take advantage of all machine learning technology already available to optimize food production, maximize yield and minimize impact in the environment.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Elias Khalil<\/strong> (Andrea Lodi, Polytechnique Montr\u00e9al)\n<ul>\n<li>New Frontiers in Learning for Discrete Optimization<\/li>\n<li>In addressing current and future societal needs, both the public and private sectors are deploying increasingly complex information and decision systems at unprecedented scales. The algorithms underlying such systems must evolve and improve rapidly to keep up with the pace. This project focuses on algorithms for Discrete Optimization, a widely used tool for decision-making and planning in industrial applications. The goal is to devise Machine Learning (ML) methods that streamline the process of algorithm design for discrete optimization, particularly in new, uncharted domains where classical paradigms may not be effective.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Kazuya Mochizuki<\/strong> (Jean-Fran\u00e7ois Arguin, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>Deep Learning to understand the LHC data<\/li>\n<li>What is our universe made of? To answer this question with the current technology, the Large Hadron Collider (LHC) has been under its stable operation since 2009, and has collected data of enormous number of proton-proton collisions, O(1e16\/year). The protons are accelerated to nearly the speed of light. Each collision reproduces the high energy state that our universe once had right after the Big Bang. The research of fundamental particles under such high energy condition is very important to better understand the laws of our universe, which might tell us the future of our cosmos. Single collision at the LHC produces O(1000) particles, whose data are collected via millions of readout channels from the detector. Therefore, the data to be analyzed at the LHC amount to O(30PB\/year), and become complex i.e. it would be a suitable target to apply and study machine learning (ML) techniques. However, many areas of the analyses have yet to be improved using advanced ML algorithms such as Deep Learning (DL). This project will accelerate the application of ML\/DL to several aspects of LHC data analyses, with particular focuses on the particle identification, and the data quality evaluation, in order to support a potential discovery of new particles.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Jonathan Por\u00e9e<\/strong> (Jean Provost, Polytechnique Montr\u00e9al)\n<ul>\n<li>Angiographie Myocardique Ultrasonore Super r\u00e9solue<\/li>\n<li>Les maladies cardiovasculaires sont responsables de plus de 30% des d\u00e9c\u00e8s dans le monde dont plus de 7 millions chaque ann\u00e9e sont imputable aux maladies coronariennes. Chez les patients pr\u00e9sentant des maladies coronariennes connues ou suspect\u00e9es, l\u2019imagerie est souvent la premi\u00e8re \u00e9tape du diagnostic. Malheureusement, aucune technique non-invasive ne permet aujourd\u2019hui de cartographier l\u2019anatomie et la fonction des vaisseaux intra myocardiques irriguant le c\u0153ur. Le d\u00e9veloppement d\u2019\u00e9chographes ultrarapides a r\u00e9cemment permis le d\u00e9veloppement d\u2019une nouvelle m\u00e9thode d\u2019angiographie super-r\u00e9solue, bas\u00e9e sur la d\u00e9tection de microbulles inject\u00e9es, permettant de cartographier des vaisseaux sanguins \u00e0 l\u2019\u00e9chelle capillaire (&lt;10 \u00b5m). Cette technique ne peut cependant pas \u00eatre directement \u00eatre appliqu\u00e9e au c\u0153ur puisqu\u2019elle n\u00e9cessite encore aujourd\u2019hui plusieurs minutes d\u2019acquisitions et est tr\u00e8s sensible au mouvement. Notre objectif principal est la mise au point d\u2019un syst\u00e8me ultrasonore de cartographie super r\u00e9solue de la micro vascularisation intra myocardique en 3D par apprentissage machine destin\u00e9e au diagnostic pr\u00e9coce des maladies coronariennes. L\u2019utilisation de r\u00e9seaux de neurones r\u00e9currents devrait permettre de pr\u00e9dire la structure et les param\u00e8tres du r\u00e9seau vasculaire et ainsi am\u00e9liorer le pronostic des patients tout en minimisant la complexit\u00e9 des examens.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Sharan Vaswani<\/strong> (Simon Lacoste-Julien, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>Theoretical Understanding of Deep Neural Networks<\/li>\n<li>Deep neural networks have led to state-of-the-art results in a wide range of applications including object detection, speech recognition, machine translation and reinforcement learning. However, the optimization techniques for training such models are not well-understood theoretically. Furthermore, it is unclear how the optimization procedure affects the ability of these models to generalize to new data. In this project, we propose to design scalable theoretically-sound optimization algorithms exploiting the underlying structure of deep networks. We also plan to investigate the interplay between optimization and generalization for these models. We hope that this project will result in improved methods for training deep neural networks.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Simon Verret<\/strong> (Yoshua Bengio, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>Apprentissage profond pour les propri\u00e9t\u00e9s \u00e9lectroniques des mat\u00e9riaux quantiques<\/li>\n<li>Certains mat\u00e9riaux ont des propri\u00e9t\u00e9s qui ne s\u2019expliquent qu\u2019avec les lois de la physique quantique: ce sont les mat\u00e9riaux quantiques. Il est souvent difficile de calculer les pr\u00e9dictions th\u00e9oriques de leur propri\u00e9t\u00e9s, comme c\u2019est le cas pour la supraconductivit\u00e9 \u00e0 haute temp\u00e9rature critique, ou les phases topologiques de la mati\u00e8re. Cela ralentit la recherche sur ces mat\u00e9riaux, et donc le d\u00e9veloppement de nouvelles technologies. En collaboration avec l\u2019Institut Quantique (IQ), \u00e0 Sherbrooke, le pr\u00e9sent projet est d\u2019utiliser les m\u00e9thodes de pointe en apprentissage profond pour am\u00e9liorer nos outils de pr\u00e9dictions pour les mat\u00e9riaux quantiques. D\u2019une part, nous cherchons \u00e0 am\u00e9liorer les avanc\u00e9e r\u00e9centes bas\u00e9es sur l\u2019apprentissage profond pour les calculs dits ab initio, qui permettent le calcul des propri\u00e9t\u00e9s \u00e9lectroniques et chimiques des mol\u00e9cules et cristaux \u00e0 partir seulement de leur configuration atomique. D\u2019autre part, nous cherchons \u00e0 int\u00e9grer l\u2019apprentissage profond aux m\u00e9thodes de pointes pour \u00e9lectrons fortement corr\u00e9l\u00e9s, c\u2019est-\u00e0-dire pour les mat\u00e9riaux o\u00f9 la configuration seule ne suffit pas, car les \u00e9lectrons interagissent fortement. Il s\u2019agit de la toute premi\u00e8re collaboration entre IVADO et l\u2019IQ, qui permettra de d\u00e9velopper une l&#8217;expertise de pointe en intelligence artificielle pour la mod\u00e9lisation de mat\u00e9riaux quantiques.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Marzieh Zare<\/strong> (Karim Jerbi, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>AI-powered investigation of the complex neuronal determinants of cognitive capacities in health, aging, and mild cognitive impairment<\/li>\n<li>Cognitive abilities and mental performance evolve across the life-span and are affected by normal and pathological aging. Understanding how brain function changes with age and how its dynamics relate to cognitive capacities or impairments would greatly contribute to the general well-being of the population and reduction of the economic burden of neurodegenerative diseases. In particular, discovering neural markers of cognitive function and predictors of dysfunction is a particularly important research goal in societies with aging populations like Canada. By combining data analytics and state-of-the-art brain signal analyses, this project aims to reveal the link between complex neural dynamics and cognitive capacities and to assess this relationship in the context of normal and pathological aging. Metrics of neural complexity and non-linear brain dynamics will be probed in large data sets consisting of neuropsychological and electrophysiological (EEG and MEG) data, including sleep EEG data collected in elderly patients with mild cognitive impairment (MCI). In order to exploit putative basic and clinical applications, both shallow learning and deep learning will be used. Furthermore, by exploring new ways to embed realistic brain network properties into deep architectures this research may also lead to novel biologically-inspired artificial neural networks that may be useful outside neuroscience.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/div><div class=\"tab-content\" ><ul>\n<li><strong>Valentina Borghesani<\/strong> (Pierre Bellec, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>How do we know what we know: neuropsychology, neuroimaging, and machine learning unraveling the neuro-cognitive substrate of semantic knowledge.<\/li>\n<li>Human intelligence has two key components: the ability to learn and that of storing a representation of what has been learned. A deeper understanding of how semantic representations are instantiated in biological neural networks (BNNs) will have a two-fold beneficial impact on society. First, it will improve clinical practice providing better diagnostic and prognostic tools for patients with impaired semantic processing. Second, it will inform the development of human-like representations in artificial neural networks (ANNs), leading towards general artificial intelligence. Through a multidisciplinary approach that includes experimental psychology, cognitive neuroimaging, and machine learning, we will shed light on how semantic representations (1) vary across individuals &#8211; both healthy volunteers and neurodegenerative patients, (2) are encoded in the brain &#8211; thanks to functional magnetic resonance imaging and magnetoencephalography, and (3) can generalize across tasks and stimuli modalities \u2013 enabling human adaptive behaviors. The extensive multimodal dataset we will acquire and analyze with state-of-the-art analytical tools will thus pave the way to groundbreaking scientific discoveries for both BNNs and ANNs.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Nicolas Loizou<\/strong> (Ioannis Mitliagkas, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>Optimization Algorithms for Machine Learning and Deep learning<\/li>\n<li>In this project, we are interested in the development of efficient algorithms for solving convex and non-convex optimization problems. Convex optimization lies at the heart of many classical machine learning tasks. In this project, one of our goals is the development of provably convergent algorithms for solving structured convex optimization problems. Interesting Directions: Define the weaker assumptions which guarantee convergence of optimization algorithms like Adam, Adagrad, SGD with momentum. What is the optimal mini-batch size of these algorithms? What is the optimal selection for learning rate and momentum parameter? What is the optimal sampling? Deep Neural Networks (DNNs) are the state-of-the art machine learning approach in many application areas. However, the optimization methods used for training such models are not well-understood theoretically. In this project we are interested in the design of novel optimization algorithms that exploring the underlying structure of DNNs. Interesting Directions: Can we theoretically provide an explanation of the heuristics (stagewise stepsize, batch normalization, etc) used in the training of DNNs? Is it possible to design methods that generalize well to new data by studying the loss landscape of DNNs? Can we design efficient distributed data-parallel algorithms with aim to accelerate the training of DNNs?<\/li>\n<\/ul>\n<\/li>\n<li><strong>Alexandra Luccioni<\/strong> (Yoshua Bengio, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>Using Generative Adversarial Networks to Visualize the Impacts of Climate Change<\/li>\n<li>It is difficult to overstate the importance of fighting climate change. A recent report from the Intergovernmental Panel on Climate Change determined that dramatic and rapid changes to the global economy are required in order to avoid mounting climate-related risks for natural and human systems. However, public awareness and concern about climate change often does not match the magnitude of threat to humans and our environment. A primary reason for this is cognitive biases which tend to downplay the importance of effects we don&#8217;t see or experience personally. Therefore, making abstract predictions of climate change impacts understandable, relatable, and well-communicated is vital in helping to overcome the barriers to public awareness and action with regards to climate change. To contribute to overcoming these challenges, we propose to use a Generative Adversarial Network (GAN) to simulate imagery of the impact that climate-change induced flooding will have on buildings and houses in North America. Our GAN can then be hosted on the Web and used as a tool to help the public understand &#8211; both rationally and viscerally &#8211; the consequences of not taking sufficient action against climate change.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Jiaxin Mao<\/strong> (Jian-Yun Nie, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>User Behavior Modeling for Intelligent Information Systems<\/li>\n<li>Intelligent information systems such as search engines, recommender systems, digital assistants, and social chatbots are ubiquitous today. Machine learning algorithms are the core components of these systems. Therefore, the development of more sophisticated machine learning models for the next generation of intelligent information systems relies on the amount and quality of the training data. As a by-product of operating these systems, we can log a large amount of user interaction data and use it to train and optimize the machine learning models. For example, users&#8217; clicks can be used as implicit relevance feedback to optimize Web search engines. However, optimizing the information system with observed user behavior logs is a non-trivial task as they only provide implicit and noisy signals and depend strongly on context. This project addresses this problem by first building reliable and generalizable user behavior models from the observed user behavior log and then utilizing them to optimize the intelligent information systems. This project will advance the research and development of intelligent information systems by solving the bottleneck of data availability.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tangi Migot<\/strong> (Dominique Orban, Polytechnique Montr\u00e9al)\n<ul>\n<li>Large scale optimization solvers in Julia for data science<\/li>\n<li>L\u2019\u00e9tude d\u2019algorithmes pour r\u00e9soudre les probl\u00e8mes d\u2019optimisation est devenue au fil des ann\u00e9es la base de la science des donn\u00e9es et par extension ses multiples applications dans des secteurs cl\u00e9s tels que la sant\u00e9, le transport, l\u2019\u00e9nergie, la finance &#8230; De nos jours, de nouveaux d\u00e9fis impliquent une quantit\u00e9 toujours grandissante de donn\u00e9es \u00e0 traiter ainsi qu\u2019un accroissement de la difficult\u00e9 des mod\u00e8les utilis\u00e9s. Ce projet a pour but de nouvelles avanc\u00e9es dans des outils num\u00e9riques en Julia pour r\u00e9soudre des probl\u00e8mes d\u2019optimisation complexe de tr\u00e8s grande taille. Dans cette \u00e9tude, nous consid\u00e9rons deux exemples que sont les probl\u00e8mes d\u2019optimisation sous contraintes d\u2019\u00e9quation aux d\u00e9riv\u00e9es partielles et les probl\u00e8mes d\u2019optimisations avec contraintes d\u00e9g\u00e9n\u00e9r\u00e9es qui surviennent en particulier dans l\u2019\u00e9tude de la th\u00e9orie des jeux.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Jeremy Nadal<\/strong> (Fran\u00e7ois Leduc-Primeau, Polytechnique Montr\u00e9al)\n<ul>\n<li>Apprentissage automatique pour des syst\u00e8mes MIMO massifs \u00e0 faible consommation d\u2019\u00e9nergie<\/li>\n<li>L&#8217;ann\u00e9e 2020 marquera le d\u00e9but du d\u00e9ploiement \u00e0 grande \u00e9chelle de la 5e g\u00e9n\u00e9ration de r\u00e9seaux cellulaires. Cependant, la question de l\u2019impact \u00e9nerg\u00e9tique de cette nouvelle g\u00e9n\u00e9ration de r\u00e9seaux se pose. Actuellement, plus de 70% des co\u00fbts \u00e9nerg\u00e9tiques des op\u00e9rateurs proviennent des infrastructures radio. Ce bilan \u00e9nerg\u00e9tique va s\u2019alourdir avec l\u2019introduction des communications en bandes millim\u00e9triques. Gr\u00e2ce \u00e0 l\u2019utilisation d\u2019un grand nombre d&#8217;antennes du c\u00f4t\u00e9 de la station de base, il est th\u00e9oriquement possible d\u2019augmenter l\u2019efficacit\u00e9 \u00e9nergique du syst\u00e8me. Cependant, les cha\u00eenes de transmission doivent \u00eatre dupliqu\u00e9es, consommant \u00e9norm\u00e9ment d&#8217;\u00e9nergie en pratique. De nombreuses solutions sont propos\u00e9es dans la litt\u00e9rature, mais celles-ci demandent une puissance calculatoire \u00e9lev\u00e9, sans certitudes d\u2019obtenir les performances optimales. Partant de ce constat, l\u2019objectif de ce projet est d\u2019\u00e9tudier et de proposer de nouvelles solutions \u00e9conomes en \u00e9nergie, performantes et implantables pour mettre en \u0153uvre les techniques de r\u00e9duction d\u2019\u00e9nergie pour des syst\u00e8mes multi-antennes. La technologie des r\u00e9seaux de neurone profonds est prometteuse pour r\u00e9soudre de tels probl\u00e8mes complexes. Une de leurs grandes forces r\u00e9side dans leur capacit\u00e9 \u00e0 apprendre les sp\u00e9cificit\u00e9s de l\u2019environnement r\u00e9el de fonctionnement. De plus, leur utilisation en t\u00e9l\u00e9communications est facilit\u00e9e par la possibilit\u00e9 d&#8217;ais\u00e9ment g\u00e9n\u00e9rer de vastes bases d&#8217;apprentissage.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Sebastien Paquette<\/strong> (Alexandre Lehmann, Universit\u00e9 de Montr\u00e9al)\n<ul>\n<li>Decoding auditory perception in cochlear implants users with machine learning<\/li>\n<li>Predicting outcomes and personalizing care have long been significant challenges in health research. One area where little progress has been made concerns Cochlear Implants (CI), which can restore hearing in the deaf. However, clinical outcomes (speech and emotion perception) vary greatly across implantees in the absence of a clear picture as to why this is the case. Due to progress in machine learning, it is believed that outcomes could be improved by identifying the specific neuro-functional markers of CI use. To address this issue, we aim to identify the neural mechanisms underlying impaired auditory processes in CI users, with an initial focus on emotion perception deficits. For this, machine learning will be used to integrate neuroimaging and acoustical data from empirical experiments into predictive models. An extensive EEG data set of CI and normal hearing participants\u2019 brain responses elicited by emotional sounds will be analyzed. For each group, we will identify: (1) the pattern of brain responses that can discriminate emotions and (2) the specific acoustic features (e.g., tempo, pitch) used for emotion perception.The identified neuro-markers will serve as a proof of concept, toward the broader implementation of machine learning to improve the quality of life of CI users.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Claudie Ratt\u00e9-Fortin<\/strong> (Jean-Fran\u00e7ois Plante, HEC Montr\u00e9al)\n<ul>\n<li>Apprentissage automatique pour la mod\u00e9lisation d\u2019\u00e9v\u00e9nements extr\u00eames<\/li>\n<li>En contexte de r\u00e9chauffement climatique, les administrations publiques devront assurer le maintien de la s\u00e9curit\u00e9 publique et contenir les impacts socio-\u00e9conomiques et environnementaux qu\u2019engendrent les \u00e9v\u00e9nements naturels extr\u00eames. La complexit\u00e9 de ces \u00e9v\u00e9nements de m\u00eame que les risques imminents qu\u2019ils apportent \u00e0 la population n\u00e9cessitent le d\u00e9veloppement de mod\u00e8les de plus en plus complexes afin d\u2019assurer une mod\u00e9lisation ad\u00e9quate de ces ph\u00e9nom\u00e8nes. L\u2019utilisation d\u2019approches plus avanc\u00e9es tels que les algorithmes d\u2019apprentissage automatique permettrait de r\u00e9pondre \u00e0 cette probl\u00e9matique en augmentant, d\u2019une part, la pr\u00e9cision des estimations mais \u00e9galement en r\u00e9pondant \u00e0 la complexit\u00e9 du probl\u00e8me qui devient \u00e9lev\u00e9e avec la dimensionnalit\u00e9 des variables \u00e0 l\u2019\u00e9tude et la d\u00e9pendance spatio-temporelle des donn\u00e9es. Une mod\u00e9lisation pr\u00e9dictive est d\u2019autant plus cruciale sachant que ces ph\u00e9nom\u00e8nes augmentent en fr\u00e9quence, en intensit\u00e9 et en dur\u00e9e en raison du r\u00e9chauffement global de la plan\u00e8te. L\u2019objectif du projet est d\u2019utiliser des algorithmes d\u2019apprentissage automatique afin d\u2019estimer les probabilit\u00e9s d\u2019occurrence d\u2019\u00e9v\u00e9nements extr\u00eames. \u00c0 terme, des outils de gestion bas\u00e9s sur l\u2019apprentissage automatique seront d\u00e9velopp\u00e9s et test\u00e9s \u00e0 des fins d\u2019implantation. Les principaux b\u00e9n\u00e9fices incluent une mod\u00e9lisation am\u00e9lior\u00e9e des \u00e9v\u00e9nements extr\u00eames pour une meilleure gestion des risques (sur les plans \u00e9conomique, social et environnemental) li\u00e9s \u00e0 ces \u00e9v\u00e9nements.<\/li>\n<\/ul>\n<\/li>\n<li><strong>Wu Yuan-Kai<\/strong> (Lijun Sun, McGill University)\n<ul>\n<li>Deep Spatiotemporal Modeling for Urban Traffic Data<\/li>\n<li>Large volumes of spatiotemporal data are increasingly collected and studied in modern transportation systems. Spatiotemporal models for traffic data are critical components of a wide range of intelligent transportation systems (ITS), such as ride sharing, transit service scheduling, signal control, and disruption management. The spatiotemporal data exhibit complex attributes, which introduce numerous challenges needs to be dealt with. Despite the abundance of spatiotemporal modeling techniques developed in different domains, it is still an open issue of making full use of the characteristics of the spatiotemporal datasets. The goal of this postdoc project is to develop new spatiotemporal models for urban traffic data based on deep learning and tensor learning. The specific objectives of this project are to: (1) characterize the spatiotemporal propagation properties of traffic data by deep spatiotemporal neural networks; (2) decouple interaction between external factors and traffic pattern by disentangle representation; (3) capture the strong regularity in collective travel behavior by low-rank tensor factorization and (4) utilize the cross-variable relationship by deep factors models. We will apply our models to large-scale and multivariate spatiotemporal data imputation and prediction. This project will lead to fundamental research advances to spatiotemporal modeling and urban intelligent transportation systems (ITS).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/div><\/div><div class=\"clear\"><\/div><\/div><\/div>\n","protected":false},"excerpt":{"rendered":"<p>COVID-19 update: Important dates for this program have been modified and are identified in red in the information below. Thank you for your understanding. Apply here &gt;&gt; IVADO\u2019s commitment to&#8230; <\/p>\n<div class=\"clear\"><\/div>\n<p><a href=\"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/\" class=\"gdlr-button with-border excerpt-read-more\">Read More<\/a><\/p>\n","protected":false},"author":14,"featured_media":0,"parent":9026,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v22.7 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>IVADO postdoctoral funding Program - IVADO<\/title>\n<meta name=\"robots\" content=\"noindex, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"IVADO postdoctoral funding Program - IVADO\" \/>\n<meta property=\"og:description\" content=\"COVID-19 update: Important dates for this program have been modified and are identified in red in the information below. Thank you for your understanding. Apply here &gt;&gt; IVADO\u2019s commitment to... Read More\" \/>\n<meta property=\"og:url\" content=\"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/\" \/>\n<meta property=\"og:site_name\" content=\"IVADO\" \/>\n<meta property=\"article:modified_time\" content=\"2020-07-07T15:45:32+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"60 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/\",\"url\":\"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/\",\"name\":\"IVADO postdoctoral funding Program - IVADO\",\"isPartOf\":{\"@id\":\"https:\/\/vieux.ivado.ca\/#website\"},\"datePublished\":\"2017-04-11T12:31:14+00:00\",\"dateModified\":\"2020-07-07T15:45:32+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\/\/vieux.ivado.ca\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"IVADO scholarships\",\"item\":\"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"IVADO postdoctoral funding Program\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/vieux.ivado.ca\/#website\",\"url\":\"https:\/\/vieux.ivado.ca\/\",\"name\":\"IVADO\",\"description\":\"Institut de valorisation des donn\u00e9es\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/vieux.ivado.ca\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"IVADO postdoctoral funding Program - IVADO","robots":{"index":"noindex","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"og_locale":"en_US","og_type":"article","og_title":"IVADO postdoctoral funding Program - IVADO","og_description":"COVID-19 update: Important dates for this program have been modified and are identified in red in the information below. Thank you for your understanding. Apply here &gt;&gt; IVADO\u2019s commitment to... Read More","og_url":"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/","og_site_name":"IVADO","article_modified_time":"2020-07-07T15:45:32+00:00","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"60 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/","url":"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/","name":"IVADO postdoctoral funding Program - IVADO","isPartOf":{"@id":"https:\/\/vieux.ivado.ca\/#website"},"datePublished":"2017-04-11T12:31:14+00:00","dateModified":"2020-07-07T15:45:32+00:00","breadcrumb":{"@id":"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/postdoctoral-scholarships\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/vieux.ivado.ca\/en\/"},{"@type":"ListItem","position":2,"name":"IVADO scholarships","item":"https:\/\/vieux.ivado.ca\/en\/ivado-scholarships\/"},{"@type":"ListItem","position":3,"name":"IVADO postdoctoral funding Program"}]},{"@type":"WebSite","@id":"https:\/\/vieux.ivado.ca\/#website","url":"https:\/\/vieux.ivado.ca\/","name":"IVADO","description":"Institut de valorisation des donn\u00e9es","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/vieux.ivado.ca\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/vieux.ivado.ca\/en\/wp-json\/wp\/v2\/pages\/7075\/"}],"collection":[{"href":"https:\/\/vieux.ivado.ca\/en\/wp-json\/wp\/v2\/pages\/"}],"about":[{"href":"https:\/\/vieux.ivado.ca\/en\/wp-json\/wp\/v2\/types\/page\/"}],"author":[{"embeddable":true,"href":"https:\/\/vieux.ivado.ca\/en\/wp-json\/wp\/v2\/users\/14\/"}],"replies":[{"embeddable":true,"href":"https:\/\/vieux.ivado.ca\/en\/wp-json\/wp\/v2\/comments\/?post=7075"}],"version-history":[{"count":0,"href":"https:\/\/vieux.ivado.ca\/en\/wp-json\/wp\/v2\/pages\/7075\/revisions\/"}],"up":[{"embeddable":true,"href":"https:\/\/vieux.ivado.ca\/en\/wp-json\/wp\/v2\/pages\/9026\/"}],"wp:attachment":[{"href":"https:\/\/vieux.ivado.ca\/en\/wp-json\/wp\/v2\/media\/?parent=7075"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}