Programme de financement de stages postdoctoraux IVADO

Objectifs du programme

• Former les futur·e·s chercheur·euse·s et professeur·e·s et plus généralement, les futur·e·s acteur·trice·s dans le secteur de la science des données, principalement dans les domaines d’excellence des membres IVADO : recherche opérationnelle, apprentissage machine et sciences de la décision;
• Promouvoir la mobilité, le recrutement et la rétention des jeunes chercheur·euse·s;
• Encourager le développement de la recherche de pointe collaborative et appliquée.

Admissibilité du·de la candidat·e et du·de la superviseur·e

• Pour le·la candidat·e au postdoctorat :
  1. Prévoir s’inscrire à un programme à HEC Montréal, Polytechnique Montréal, l’Université de Montréal, l’Université McGill ou l’Université de l’Alberta.
  2. Avoir reçu son premier doctorat depuis moins de cinq ans au moment de la demande ou prévoir de l’obtenir à la date de l’annonce des résultats. IVADO sera flexible pour les candidat·e·s justifiant les interruptions de carrière et les circonstances particulières, nous invitons à l’indiquer dans votre demande (p.ex. pour cause de maternité ou de maladie).
  3. La priorité sera donnée aux candidat·e·s ayant eu leur affiliation PhD principale à l’extérieur du Québec. Cette mesure vise à promouvoir l’attraction des chercheur·euse·s internationaux·ales talentueux·euses.
• Pour le·la professeur·e présentant la demande (superviseur·e) :
  1. Être un·e professeur·e de l’une des institutions suivantes : HEC Montréal, Polytechnique Montréal ou l’Université de Montréal;
  2. Les professeur·e·s de l’Université de l’Alberta et de l’Université McGill peuvent être superviseur·e·s à condition qu’ils·elles soient également membres de plein droit de l’un des groupes de recherche d’IVADO (Mila, CIRRELT, GERAD, CERC Science des données, CRM, Tech3Lab);
  3. Les statuts admissibles pour les professeur·e·s sont : professeur·e adjoint·e, professeur·e agrégé·e, professeur·e titulaire, professeur·e sous-octroi, professeur·e chercheur·euse, chercheur·euse invité·e. Les professeur·e·s associé·e·s ne sont pas admissibles.
  4. Ne pas avoir été le·la directeur·trice ou le·la codirecteur·trice du·de la candidat·e en tant que doctorant·e;
  5. Ne pas présenter plus d’une demande de candidature pour ce concours.
  6. À la date d’octroi limite (1er octobre 2020), ne pas superviser plus de deux stagiaires postdoctoraux·ales financé·e·s par ce programme (financement de stages postdoctoraux IVADO).

Début de la bourse

Date de début du financement : 1er juillet, 1er octobre 2020 ou 1er janvier 2021

Montant et conditions de versement

Les fonds (salaires et remboursements de réinstallation potentiels) seront transférés au Bureau de la recherche de l’université du·de la superviseur·e, et l’université paiera le·la chercheur·euse postdoctoral·e en fonction de ses propres règles. Pour les projets nécessitant une approbation éthique, les fonds ne seront pas débloqués tant que l’approbation ne sera pas obtenue. Certains projets, notamment en partenariat, pourraient avoir besoin d’accords spécifiques, par exemple en ce qui concerne la propriété intellectuelle.

Le financement pourra être réduit, retenu, retardé ou annulé lors de situations particulières qui seront explicitées dans la lettre d’octroi.

Processus du concours

Évaluation et critères

Les propositions seront passées en revue pour vérifier les exigences du programme (demande incomplète, trop longue, superviseur·e ou candidat·e non admissible, etc.) et l’adéquation du projet de recherche soumis avec la science des données. Seules les demandes répondant aux exigences seront transmises au comité d’évaluation.

Le comité d’évaluation sera composé de professeur·e·s bien au fait des domaines d’excellence d’IVADO, et qui ne présenteront aucun·e candidat·e. Selon la disponibilité des évaluateur·trice·s, IVADO met l’accent sur la constitution d’un comité paritaire. En raison de la petite taille de la communauté dans certains domaines, il pourrait être difficile de trouver des examinateur·trice·s pertinent·e·s ne présentant aucun·e candidat·e. Face à une telle situation, un·e évaluateur·trice pourrait être appelé·e à évaluer un·e candidat·e bien qu’il·elle participe lui·elle-même au concours; un·e examinateur·trice externe pourrait également être appelé·e. Le comité veillera par tous les moyens à ce que l’évaluateur·trice n’influe pas le classement de sa propre application.

Le comité d’évaluation procédera ensuite au classement des candidat·e·s selon l’excellence de leur dossier, mais aussi selon l’adéquation du projet dans le cadre général d’IVADO, qui est de promouvoir la collaboration multidisciplinaire et la diversité dans la science des données. En ce qui regarde l’excellence du dossier du·de la candidat·e, le comité s’intéressera plus spécifiquement :

• à ses contributions à la recherche (impact scientifique, qualité de la recherche, productivité et financements obtenus)
• à la qualité de sa thèse de doctorat et à son excellence académique,
• à l’étendue et à la portée de son expérience (expériences pluridisciplinaires, expérience professionnelle, activités parascolaires ou extra-universitaires, collaborations, services à la communauté scientifique, contribution à la société, etc.)
• et à l’adéquation de l’expérience avec le projet proposé.

L’ordonnancement des candidat·e·s pour le financement en partenariat sera basé en plus sur le potentiel de recherche appliquée du projet.

Le comité d’évaluation procédera au classement des candidat·e·s demandant un financement postdoctoral régulier et en partenariat. Pour les candidat·e·s demandant un financement postdoctoral régulier, des financements Fellow éventuels pourront être attribués en séance par le comité d’évaluation pour les candidatures exceptionnelles.

Suite à une résolution du comité scientifique d’IVADO, le comité d’évaluation ne produira pas de commentaires sur l’évaluation effectuée.

Finalisation du dossier et engagements des chercheur·euse·s postdoctoraux

Le·la chercheur·euse postdoctoral·e s’engage notamment à :

• Être physiquement présent·e à l’université de son·sa superviseur·e, ou de partager son temps entre son université d’attache et l’entreprise/organisation partenaire en cas de financement en partenariat;
• Participer à la communauté et aux activités IVADO, incluant par exemple :
  • les présentations sur leur propre recherche;
  • les activités de formation ou de diffusion des connaissances;
  • les consultations;
  • le soutien lors de différentes activités qui font normalement partie d’une carrière de recherche (mentorat, notamment dans le cadre du projet SEUR, participation à des évaluations, coorganisation d’événements, etc.);
• Reconnaître qu’il·elle fait partie d’une communauté universitaire, à laquelle il·elle contribuera;
• Se soumettre à la politique des trois organisations sur le libre accès aux publications. Il·elle est encouragé·e à publier ses productions de recherche (publications, enregistrement oral des présentations, code source, bases de données, etc.) dans le respect des règles de propriété intellectuelle applicables dans son cas particulier;
• Reconnaître le soutien d’IVADO et d’Apogée / CFREF ou du FRQ dans la diffusion des résultats de recherche et plus généralement dans les diverses activités auxquelles le·la chercheur·euse postdoctoral·e participera.

Le·la superviseur·e s’engage notamment à :

• Fournir un environnement de travail qui convient à l’achèvement du projet;
• Superviser son·sa chercheur·euse postdoctoral·e.

FAQ

• Y a-t-il un format particulier pour la préparation du CV?
  • Non, il n’y a pas de format particulier pour le CV.
• Y a-t-il des règles spécifiques pour les lettres de recommandation?
  • Il n’y a pas de règle spécifique pour les lettres de recommandation.
• Est-ce que les candidat·e·s peuvent eux-mêmes envoyer les lettres de recommandation ?
  • Non, les lettres de recommandation devront être téléchargées sur la plateforme du concours par leur auteur·e.
• Est-ce que je peux joindre mes relevés de notes non officiels?
  • Non, vous devez nous numériser et joindre à la demande tous vos relevés de notes officiels incluant tous vos résultats en cours. 
• J’ai fait mon doctorat dans un pays dans lequel il n’y avait pas de relevé de notes pour le doctorat. Que dois-je faire ?
  • Vous devez le mentionner dans votre dossier de candidature et fournir vos relevés de Maîtrise/Master à la place.
• Quelles sont les conditions d’utilisation de la bourse?
  • Un exemple de lettre est disponible ici.
• Puis-je avoir une autre activité rémunérée pendant mon stage postdoctoral, comme du conseil?
  • Le financement est d’un montant qui devrait permettre au·à la stagiaire de se concentrer exclusivement sur sa recherche, mais des activités complémentaires sont tout aussi importantes pour la formation du·de la stagiaire. Pour concilier ces deux aspects, il est acceptable d’avoir des activités rémunérées:
    • Qui respectent les politiques de l’établissement d’attache relativement aux autres sources de revenu.
    • Qui n’empêchent pas le stagiaire de se consacrer aux travaux pour lesquels il·elle est financé·e par IVADO comme s’il·elle le faisait à temps plein.
• Est-ce que le financement d’IVADO est cumulable avec d’autres financements?
  • Ce financement n’est pas cumulable avec d’autres bourses issues de financements CRSNG, CRSH, IRSC ou IVADO. Nous n’encourageons pas le cumul de bourses/financements issus d’autres sources de financement, mais nous ne l’interdisons pas non plus, car il peut se justifier dans certains cas.
• Quels sont les professeur·e·s éligibles à participer à une demande?
  • Pour le·la chercheur·euse principal·e superviseur·e, les contraintes d’affiliation sont d’être professeur·e :
    • soit à HEC Montréal, Polytechnique Montréal ou l’Université de Montréal, sans autres contraintes
    • soit à l’Université McGill ou l’université d’Alberta, mais ces professeur·e·s doivent en plus être membres de l’un des groupes de recherche suivants : CIRRELT, GERAD, Mila ou Chaire d’Excellence de Recherche du Canada en prise de décision en temps réel, CRM, Tech3Lab.
  • Pour le·la chercheur·euse principal·e, les statuts admissibles sont :
    • Professeur·e adjoint·e, Professeur·e agrégé·e, professeur·e titulaire
    • Professeur·e sous octroi
    • Professeur·e chercheur·e
    • Chercheur·euse invité·e
    • Les professeur·e·s associé·e·s ne sont pas admissibles
    • Un changement de statut ou d’affiliation du·de la chercheur·euse principal·e en cours de subvention pourrait mener à l’arrêt de celle-ci.

Bourses en partenariat

• Est-il possible de postuler à un financement « en partenariat » sans avoir de partenaire au moment de la demande?
  • Non malheureusement, il faut que vous ayez trouvé votre partenaire avant de soumettre votre demande. Une lettre d’engagement de votre partenaire est d’ailleurs demandée.
• Pour les bourses en partenariat, y a-t-il des règles spécifiques pour la rédaction de la lettre de confirmation du partenaire et par qui doit-elle être rédigée?
  • La lettre de confirmation doit être rédigée par l’encadrant du projet dans l’entreprise, et doit contenir le sujet/titre de votre projet et le montant de leur engagement financier (35 000 $/an pour deux ans).

D’autres questions? Veuillez les soumettre à programmes-excellence@ivado.ca

L’ensemble du processus de soumission de dossier se passe à travers cette plateforme dédiée: https://ivado.smapply.io/ (prochaine ouverture prévue : 2 mars 2020).

Les candidatures envoyées par courriel seront refusées.

Le dossier comprendra :

• un questionnaire à remplir sur la plateforme DONT une description vulgarisée du projet (longueur d’une page maximum);
  • Vous pouvez consulter ici un exemplaire de questionnaire complété

• le C.V. de l’étudiant·e, dans un format libre;
• les relevés de notes officiels du doctorat (préciser l’échelle de notation pour les universités non canadiennes);
• la description du projet (une page maximum incluant les références);
• un minimum de deux lettres et un maximum de trois lettres de recommandation (incluant une du·de la superviseur·e· (en cours ou potentiel·le) du stage postdoctoral)
•  une lettre de confirmation du partenaire (si le·la candidat·e et le·la superviseur·e veulent explicitement un financement postdoctoral en partenariat).

• Behrouz Babaki (Polytechnique Montréal, Gilles Pesant)
  • 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 ‘learned models’. The second task is studied by the operations research community under the label of ‘optimization’. 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.
• Maxime Laborde (McGill, Adam Oberman)
  • 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.
• Tien Mai (Université de Montréal, Teodor Gabriel Crainic)
  • 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.
• Abbas Mehrabian (McGill, Luc Devroye)
  • 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.
• Patrick Munroe (Polytechnique Montréal, François Soumis)
  • Gestion en temps réel du cargo aérien. Le projet à moyen terme est le développement d’un système de gestion du cargo dans les compagnies aériennes en commençant avec Air Canada. Ce système traitera la planification stratégique, tactique et l’opération en temps-réel. Le niveau stratégique évalue des scénarios à long terme sur l’organisation du réseau, les marchés à développer, les alliances à conclure. Le niveau tactique optimise le choix des itinéraires entre chaque paire de villes pour une semaine type d’une saison. Durant l’opération, les vendeurs pourront obtenir en ligne le meilleur itinéraire pour acheminer une nouvelle commande et le prix de revient. À chaque niveau de décision, il faut estimer la demande pour l’horizon considéré et optimiser l’acheminement de cette demande dans le réseau de transport comprenant des avions tout cargo, l’espace disponible dans les soutes des vols passagers, des sous-contrats avec d’autres transporteurs aériens et routiers. La recherche portera sur le développement de nouvelles méthodes d’estimation de la demande et d’optimisation de l’acheminement dans un grand réseau.
• Maria Isabel Restrepo Ruiz (Polytechnique Montréal, Nadia Lahrichi)
  • 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’ 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.
• Anne-Lise Saive (Université de Montréal, Karim Jerbi)
  • 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.
• Rabih Salhab (HEC Montréal, Georges Zaccour)
  • 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.
• Kristen Schell (Polytechnique Montréal, Miguel Anjos)
  • Hydro-Québec 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-Québec 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.
• Jean-François Spinella (Université de Montréal, Guy Sauvageau)
  • 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.
• Yu Zhang (Université de Montréal, Pierre Bellec)
  • 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’s disease and evaluating the treatment effects of precision medicine.

• Jonathan Binas (Université de Montréal, Yoshua Bengio)
  • 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,
    brains 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.
• Marco Bonizzato (Université de Montréal, Marina Martinez)
  • 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’s own residual networks and increases voluntary control of leg movement with long lasting beneficial effects for recovery. “Fire together, wire together” 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.
• Elie Bou Assi (Université de Montréal, Dang K. Nguyen)
  • 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.
• Quentin Cappart (Polytechnique Montréal, Louis-Martin Rousseau)
  • L’optimisation combinatoire occupe une place prépondérante dans notre société actuelle. Que ce soit la logistique, le transport ou la gestion financière, tous ses domaines se retrouvent confrontés à des problèmes pour lesquels on recherche la meilleure solution. Cependant, un grand nombre de problèmes très complexes reste encore hors de portée des méthodes d’optimisation actuelles. C’est pourquoi, l’amélioration de ces techniques est un sujet crucial. Parmi ces dernières, les diagrammes de décisions semblent avoir un avenir prometteur. Un diagramme de décision est une structure qui permet de représenter de manière compacte un problème tout en préservant ses caractéristiques. Cependant, leur efficacité est extrêmement dépendante de l’ordre des variables utilisé pour leur construction. L’objectif de ce projet est d’utiliser les méthodes récentes d’apprentissage automatique pour ordonner les variables lors de la construction d’un diagramme de décision. Les contributions de ce projet permettront la résolution de problèmes combinatoires plus complexes, et plus larges que ce que peuvent faire les méthodes de l’état de l’art. Nous nous consacrerons principalement aux problèmes réels liés au transport et à la logistique. Ce projet sera effectué en partenariat avec l’entreprise Element-AI.
• Jasmin Coulombe-Huntington (Université de Montréal, Micheal Tyers)
  • 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 >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.
• Pouria Dasmeh (Université de Montréal, Adrian Serohijos)
  • 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 ~ $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.
• Benoit Delcroix (Polytechnique Montréal, Michel Bernier)
  • Un défi majeur dans le secteur du bâtiment est l’’absence de systèmes continus de suivi de la performance et d’évaluation des écarts de performance entre la situation observée et celle désirée. L’opération non-optimale des systèmes de Chauffage, Ventilation et Conditionnement d’Air (CVCA) entraîne des pertes énergétiques et de confort des occupants. Le secteur du bâtiment représente environ un tiers de la consommation énergétique au Québec et au Canada. Ainsi, des mesures d’’efficacité dans ce secteur produisent des impacts positifs majeurs. L’idée de ce projet est d’utiliser des méthodes d’apprentissage profond pour exploiter les larges jeux de données générés par les systèmes CVCA. Le but final est d’automatiser la détection et le diagnostic des anomalies, et d’optimiser l’opération des équipements. Les bénéfices incluent une gestion améliorée de l’énergie et une meilleure prise en compte du confort des occupants. Au terme de ce projet, des outils de détection / diagnostic / contrôle basés sur l’apprentissage profond seront développés et testés à des fins d’implantation dans des bâtiments réels.
• Golnoosh Farnadi (Polytechnique Montréal, Michel Gendreau)
  • The increasing use of algorithmic decision-making in domains that affect people’s 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.
• Kuldeep Kumar (Université de Montréal, Sébastien Jacquemont)
  • 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.
• Elizaveta Kuznetsova (Polytechnique Montréal, Miguel Anjos)
  • 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.
• Tarek Lajnef (Université de Montréal, Karim Jerbi)
  • 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.
• Neda Navidi (Polytechnique Montréal, Nicolas Saunier)
  • 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’ 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’s position on a road segment, which provides more contextual information like road geometry and conditions, historical risk of the segment and other drivers’ 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.
• Nurit Oliker (Université de Montréal, Bernard Gendron)
  • 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.
• Camilo Ortiz Astorquiza (Université de Montréal, Emma Frejinger)
  • 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’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.
• Musa Ozboyaci (Université de Montréal, Sebastian Pechmann)
  • 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’s and Parkinson’s. 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.
• Maximilian Puelma Touzel (Université de Montréal, Guillaume Lajoie)
  • 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’’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.
• Raphael Harry Frederico Ribeiro Kramer (Polytechnique Montréal, Guy Desaulniers)
  • 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.
• Joshua Stipancic (HEC Montréal, Aurélie Labbe)
  • 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.

• Eugene Belilovsky (Aaron Courville, Université de Montréal)
  • Towards Learning Language Based Navigation in Visually Rich 3-D Environments
  • 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’s 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.
• Glen Berseth (Christopher Pal, Polytechnique Montréal)
  • Visual Imitation Learning With Partial Information
  • 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.
• Jhelum Chakravorty (Doina Precup, McGill University)
  • Temporal abstraction in multi-agent environment
  • 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’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.
• Ricardo de Azambuja (Giovanni Beltrame, Polytechnique Montréal)
  • High Fidelity Data Collection for Precision Agriculture with Drone Swarms
  • 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 – UAVs) can only see from a fixed perspective: above. Additionally, according to PwC there’s a $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.
• Elias Khalil (Andrea Lodi, Polytechnique Montréal)
  • New Frontiers in Learning for Discrete Optimization
  • 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.
• Kazuya Mochizuki (Jean-François Arguin, Université de Montréal)
  • Deep Learning to understand the LHC data
  • 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.
• Jonathan Porée (Jean Provost, Polytechnique Montréal)
  • Angiographie Myocardique Ultrasonore Super résolue
  • Les maladies cardiovasculaires sont responsables de plus de 30% des décès dans le monde dont plus de 7 millions chaque année sont imputable aux maladies coronariennes. Chez les patients présentant des maladies coronariennes connues ou suspectées, l’imagerie est souvent la première étape du diagnostic. Malheureusement, aucune technique non-invasive ne permet aujourd’hui de cartographier l’anatomie et la fonction des vaisseaux intra myocardiques irriguant le cœur. Le développement d’échographes ultrarapides a récemment permis le développement d’une nouvelle méthode d’angiographie super-résolue, basée sur la détection de microbulles injectées, permettant de cartographier des vaisseaux sanguins à l’échelle capillaire (<10 µm). Cette technique ne peut cependant pas être directement être appliquée au cœur puisqu’elle nécessite encore aujourd’hui plusieurs minutes d’acquisitions et est très sensible au mouvement. Notre objectif principal est la mise au point d’un système ultrasonore de cartographie super résolue de la micro vascularisation intra myocardique en 3D par apprentissage machine destinée au diagnostic précoce des maladies coronariennes. L’utilisation de réseaux de neurones récurrents devrait permettre de prédire la structure et les paramètres du réseau vasculaire et ainsi améliorer le pronostic des patients tout en minimisant la complexité des examens.
• Sharan Vaswani (Simon Lacoste-Julien, Université de Montréal)
  • Theoretical Understanding of Deep Neural Networks
  • 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.
• Simon Verret (Yoshua Bengio, Université de Montréal)
  • Apprentissage profond pour les propriétés électroniques des matériaux quantiques
  • Certains matériaux ont des propriétés qui ne s’expliquent qu’avec les lois de la physique quantique: ce sont les matériaux quantiques. Il est souvent difficile de calculer les prédictions théoriques de leur propriétés, comme c’est le cas pour la supraconductivité à haute température critique, ou les phases topologiques de la matière. Cela ralentit la recherche sur ces matériaux, et donc le développement de nouvelles technologies. En collaboration avec l’Institut Quantique (IQ), à Sherbrooke, le présent projet est d’utiliser les méthodes de pointe en apprentissage profond pour améliorer nos outils de prédictions pour les matériaux quantiques. D’une part, nous cherchons à améliorer les avancée récentes basées sur l’apprentissage profond pour les calculs dits ab initio, qui permettent le calcul des propriétés électroniques et chimiques des molécules et cristaux à partir seulement de leur configuration atomique. D’autre part, nous cherchons à intégrer l’apprentissage profond aux méthodes de pointes pour électrons fortement corrélés, c’est-à-dire pour les matériaux où la configuration seule ne suffit pas, car les électrons interagissent fortement. Il s’agit de la toute première collaboration entre IVADO et l’IQ, qui permettra de développer une l’expertise de pointe en intelligence artificielle pour la modélisation de matériaux quantiques.
• Marzieh Zare (Karim Jerbi, Université de Montréal)
  • AI-powered investigation of the complex neuronal determinants of cognitive capacities in health, aging, and mild cognitive impairment
  • 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.

Valentina Borghesani (Pierre Bellec, Université de Montréal) 

• How do we know what we know: neuropsychology, neuroimaging, and machine learning unraveling the neuro-cognitive substrate of semantic knowledge.
• 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 – both healthy volunteers and neurodegenerative patients, (2) are encoded in the brain – thanks to functional magnetic resonance imaging and magnetoencephalography, and (3) can generalize across tasks and stimuli modalities – 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.

• Nicolas Loizou (Ioannis Mitliagkas, Université de Montréal)
  • Optimization Algorithms for Machine Learning and Deep learning
  • 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?

• Alexandra Luccioni (Yoshua Bengio, Université de Montréal)
  • Using Generative Adversarial Networks to Visualize the Impacts of Climate Change
  • 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’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 – both rationally and viscerally – the consequences of not taking sufficient action against climate change.

• Jiaxin Mao (Jian-Yun Nie, Université de Montréal)
  • User Behavior Modeling for Intelligent Information Systems
  • 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’ 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. 

• Tangi Migot (Dominique Orban, Polytechnique Montréal)
  • Large scale optimization solvers in Julia for data science
  • L’étude d’algorithmes pour résoudre les problèmes d’optimisation est devenue au fil des années la base de la science des données et par extension ses multiples applications dans des secteurs clés tels que la santé, le transport, l’énergie, la finance … De nos jours, de nouveaux défis impliquent une quantité toujours grandissante de données à traiter ainsi qu’un accroissement de la difficulté des modèles utilisés. Ce projet a pour but de nouvelles avancées dans des outils numériques en Julia pour résoudre des problèmes d’optimisation complexe de très grande taille. Dans cette étude, nous considérons deux exemples que sont les problèmes d’optimisation sous contraintes d’équation aux dérivées partielles et les problèmes d’optimisations avec contraintes dégénérées qui surviennent en particulier dans l’étude de la théorie des jeux.

• Jeremy Nadal (François Leduc-Primeau, Polytechnique Montréal)
  • Apprentissage automatique pour des systèmes MIMO massifs à faible consommation d’énergie
  • L’année 2020 marquera le début du déploiement à grande échelle de la 5e génération de réseaux cellulaires. Cependant, la question de l’impact énergétique de cette nouvelle génération de réseaux se pose. Actuellement, plus de 70% des coûts énergétiques des opérateurs proviennent des infrastructures radio. Ce bilan énergétique va s’alourdir avec l’introduction des communications en bandes millimétriques. Grâce à l’utilisation d’un grand nombre d’antennes du côté de la station de base, il est théoriquement possible d’augmenter l’efficacité énergique du système. Cependant,  les chaînes de transmission doivent être dupliquées, consommant énormément d’énergie en pratique. De nombreuses solutions sont proposées dans la littérature, mais celles-ci demandent une puissance calculatoire élevé, sans certitudes d’obtenir les performances optimales. Partant de ce constat, l’objectif de ce projet est d’étudier et de proposer de nouvelles solutions économes en énergie, performantes et implantables pour mettre en œuvre les techniques de réduction d’énergie pour des systèmes multi-antennes. La technologie des réseaux de neurone profonds est prometteuse pour résoudre de tels problèmes complexes. Une de leurs grandes forces réside dans leur capacité à apprendre les spécificités de l’environnement réel de fonctionnement. De plus, leur utilisation en télécommunications est facilitée par la possibilité d’aisément générer de vastes bases d’apprentissage. 

• Sebastien Paquette (Alexandre Lehmann, Université de Montréal)
  • Decoding auditory perception in cochlear implants users with machine learning
  • 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’ 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.

• Claudie Ratté-Fortin (Jean-François Plante, HEC Montréal)
  • Apprentissage automatique pour la modélisation d’événements extrêmes
  • En contexte de réchauffement climatique, les administrations publiques devront assurer le maintien de la sécurité publique et contenir les impacts socio-économiques et environnementaux qu’engendrent les événements naturels extrêmes. La complexité de ces événements de même que les risques imminents qu’ils apportent à la population nécessitent le développement de modèles de plus en plus complexes afin d’assurer une modélisation adéquate de ces phénomènes. L’utilisation d’approches plus avancées tels que les algorithmes d’apprentissage automatique permettrait de répondre à cette problématique en augmentant, d’une part, la précision des estimations mais également en répondant à la complexité du problème qui devient élevée avec la dimensionnalité des variables à l’étude et la dépendance spatio-temporelle des données. Une modélisation prédictive est d’autant plus cruciale sachant que ces phénomènes augmentent en fréquence, en intensité et en durée en raison du réchauffement global de la planète. L’objectif du projet est d’utiliser des algorithmes d’apprentissage automatique afin d’estimer les probabilités d’occurrence d’événements extrêmes. À terme, des outils de gestion basés sur l’apprentissage automatique seront développés et testés à des fins d’implantation. Les principaux bénéfices incluent une modélisation améliorée des événements extrêmes pour une meilleure gestion des risques (sur les plans économique, social et environnemental) liés à ces événements. 

• Wu Yuan-Kai (Lijun Sun, McGill University)
  • Deep Spatiotemporal Modeling for Urban Traffic Data
  • 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).