IVADO/MILA/DSI Deep Learning School 5th edition

December 2-6, 2019 | Vancouver (English)

About

Summary

Deep learning is a machine learning technique that has significantly improved previous results in computer vision, speech recognition, machine translation and other areas. Many other areas are affected by this new technology, or will be. In response to the interest generated by this technology, and in response to training needs, IVADO and Mila are partnering with the UBC Data Science Institute to offer this training in Vancouver from December 2 to 6, 2019.

Target audience

The content of this school is mainly aimed at industry professionals and SMEs with basic knowledge of mathematics and programming (engineers, computer scientists, statisticians, technical project managers, product managers, systems engineers, etc.), but professors and graduate students in science or engineering (mainly those who are not yet familiar with deep learning) may also find it interesting.

Prerequisites

A minimal knowledge of programming (ideally Python) and basic knowledge in mathematics (linear algebra, statistics) is desirable.

Objectives

At the end of the training week, participants should be able to:

  • Understand the basics and terminology related to deep learning
  • Understand the methodology for carrying out a project in deep learning
  • Identify the types of neural networks to use to solve different types of problems
  • Get familiar with deep learning libraries through practical and tutorial sessions

Dates and place

December 2-6, 2019, Vancouver

UBC Nest South Ballroom
6133 University Boulevard
Vancouver, BC

View Map

Contact

For any comments, do not hesitate to contact us at the following email address: formations@ivado.ca.

This school is made possible by the Canada First Research Excellence Fund.

Dates and places

December 2-6, 2019, Vancouver, English

Confirmed Speakers

Gaétan Marceau Caron 

Applied Research Scientist
Mila – Institut Québécois d’Intelligence Artificielle

Golnoosh Farnadi

Postdoctoral Researcher
Mila – Institut Québécois d’Intelligence Artificielle

Jeremy Pinto

Applied Research Scientist
Mila – Institut Québécois d’Intelligence Artificielle

Michiel van de Panne

Professor, Canada Research Chair
Associate Head for Research and Faculty Affairs

Mirko Bronzi

Applied Research Scientist
Mila – Institut Québécois d’Intelligence Artificielle

Evgueni Loukipoudis

CTO of Canada’s Digital Technology Supercluster

Fred Popowich

Computing Scientist at Simon Fraser University
Scientific Director of SFU’s Big Data Initiative

Raymond T Ng

Director, Data Science Institute, UBC
Professor, Computer Science, UBC
Canada Research Chair in Data Science and Analytics
Chief Informatics Officer, PROOF (Prevention of Organ Failure) Centre

Program

Machine Learning

9AM – 09:10AM: Welcome

Welcome words by IVADO and Mila

09:10AM – 10:15AM: Presentation

Machine learning and experimental protocol

Gaétan Marceau Caron

10:15AM – 10:45AM: Break

10:45AM – 12PM: Presentation

Introduction to Machine Learning

Gaétan Marceau Caron

12PM – 1:30PM: Lunch

1:30PM – 2:45PM: Presentation

Machine learning tools

Jeremy Pinto

2:45PM – 3:15PM: Break

3:15 – 4:30PM: Tutorial

Data & metrics with pyTorch

Deep Learning

9AM – 10:15AM: Presentation

Introduction to deep learning

Gaétan Marceau Caron

10:15AM – 10:45AM: Break

10:45AM – 12PM: Presentation

Computational graph & backpropagation

Gaétan Marceau Caron

12PM – 1:30PM: Lunch

1:30PM – 2:45PM: Presentation

Optimization in deep learning

Gaétan Marceau Caron

2:45PM – 3:15PM: Break

3:15PM – 4:30PM: Tutorial

Categorical data with multilayer perceptron (MLP)

CNN

9AM – 10:15AM: Presentation

Introduction to convolutional neural networks, part I

Jeremy Pinto

10:15AM – 10:45AM: Break

10:45AM – 12PM: Presentation

Introduction to convolutional neural networks, part II

Jeremy Pinto

12PM – 1:30PM: Lunch

1:30PM – 2:45PM: Presentation

Convolutional neural network architectures

Jeremy Pinto

2:45PM – 3:15PM: Break

3:15PM – 4:30PM: Tutorial

Getting started with convolutional neural networks

RNN

9AM – 10:15AM: Presentation

Introduction to recurrent neural networks

Mirko Bronzi

10:15AM – 10:45AM: Break

10:45AM – 12PM: Presentation

Sequence to sequence models

Mirko Bronzi

12PM – 1:30PM: Lunch

1:30PM – 2:45PM: Presentation

Natural language processing

Mirko Bronzi

2:45PM – 3:15PM: Break

3:15PM – 4:30PM: Tutorial

Recurrent neural networks

9AM – 10:15AM: Presentation

Reinforcement Learning

Dr. Michiel van de Panne (Professor, UBC Computer Science)

10:15AM – 10:30AM: Coffee Break

10:30AM – 12PM: Presentation

Reinforcement Learning

Dr. Michiel van de Panne (Professor, UBC Computer Science)

12PM – 1PM: Lunch Break

1PM – 2:45PM: Presentation

Ethics in AI: Bias and discrimination in Machine Learning

Dr. Golnoosh Farnadi (Researcher at Polytechnique Montréal)

2:45PM – 3:00PM: Coffee Break

3:00PM – 4:00PM: Presentation

Ethics in AI Discussion Panel

    • Evgueni Loukipoudis
      CTO of Canada’s Digital Technology Supercluster.
    • Fred Popowich
      Computing Scientist at Simon Fraser University
      Scientific Director of SFU’s Big Data Initiative.
    • Raymond T Ng
      Director, Data Science Institute, UBC
      Professor, Computer Science, UBC
      Canada Research Chair in Data Science and Analytics
      Chief Informatics Officer, PROOF (Prevention of Organ Failure) Centre
    • Golnoosh Farnadi
      IVADO post-doctoral fellow at Polytechnique Montréal