Courses and schedules - Winter 2021 (preliminary list)
See the full list of DIRO courses
| Professor | Course | Description | Credits | Schedule | Dates |
|---|---|---|---|---|---|
| Simon Lacoste-Julien | IFT 6132 -Advanced Structures Prediction and Optimization | Structured prediction is the problem of learning a prediction mapping between inputs and structured outputs, i.e. outputs that are made of interrelated parts often subject to constraints. Examples include predicting trees, orderings, alignments, etc., and appear in many applications from computer vision, natural language processing and computational biology among others. This is an advanced machine learning course that will focus on the fundamental principles and related tools for structured prediction. The course will review the state of the art, tie older and newer approaches together, as well as identify open questions. It will consist of a mix of faculty lectures, class discussions and paper presentations by students, as well as a research project. Prerequisite: I will assume that most of the content of IFT 6269 Probabilistic Graphical Models is known by the students. | 4 | Tue. 2:30 – 4:30 Thurs. 1:30 – 3:30 | 2021-01-12 |
| Aaron Courville | IFT6135 – Representation Learning (Winter 2019) | This is a course on representation learning in general and deep learning in particular. Deep learning has recently been responsible for a large number of impressive empirical gains across a wide array of applications including most dramatically in object recognition and detection in images and speech recognition. In this course we will explore both the fundamentals and recent advances in the area of deep learning. Our focus will be on neural network-type models including convolutional neural networks and recurrent neural networks such as LSTMs. We will also review recent work on attention mechanism and efforts to incorporate memory structures into neural network models. We will also consider some of the modern neural network-base generative models such as Generative Adversarial Networks and Variational Autoencoders. | 4 | TBD | TBD |
| Ioannis Mitliagkas | IFT-6085 – Theoretical principles for deep learning (Winter 2020) | Research in deep learning produces state-of-the-art results on a number of machine learning tasks. Most of those advances are driven by intuition and massive exploration through trial and error. As a result, theory is currently lagging behind practice. The ML community does not fully understand why the best methods work. Why can we reliably optimize non-convex objectives? How expressive are our architectures, in terms of the hypothesis class they describe? Why do some of our most complex models generalize to unseen examples when we use datasets orders of magnitude smaller than what the classic statistical learning theory deems sufficient? A symptom of this lack of understanding is that deep learning methods largely lack guarantees and interpretability, two necessary properties for mission-critical applications. More importantly, a solid theoretical foundation can aid the design of a new generation of efficient methods—sans the need for blind trial-and-error-based exploration. In this class we will go over a number of recent publications that attempt to shed light onto these questions. Before discussing the new results in each paper we will first introduce the necessary fundamental tools from optimization, statistics, information theory and statistical mechanics. The purpose of this class is to get students engaged with new research in the area. To that end, the majority of credit will be given for a class project report and presentation on a relevant topic. Note: This is meant to be an advanced graduate class for students who want to engage in theory-driven deep learning research. We will introduce some theoretical tools necessary, but start with the assumption that students are comfortable with:
If you have not taken classes on all of the above topics, this class is not designed for you. You should take another class instead. | 4 | TBD | TBD |
| Guillaume Rabusseau | IFT 6760A – Matrix and tensor factorization for ML | The goal of this course is to present an overview of linear and multilinear algebra techniques for designing/analyzing ML algorithms and models, and to engage students with new research in the area. – Fundamental notions of linear and multilinear algebra. – Old and new ML methods leveraging matrix and tensor decomposition: PCA/CCA, collaborative filtering, spectral graph clustering, spectral methods for HMM, K-FAC, spectral normalization, tensor method of moments, NN/MRF compression, tensor regression/completion, etc. – Open problems. | 4 | Tue. 12:30 – 2:30 Thu. 11:30 – 1:30 | TBD |
| Irina Rish | IFT 6760b – Continual Learning: Towards “Broad” AI (Winter 2020) | Stephen Hawking famously said, ‘Intelligence is the ability to adapt to change.’ While today’s AI systems can achieve impressive performance in specific tasks, from accurate image recognition to super-human performance in games such as Go and chess, they are still quite “narrow”, i.e. not being able to easily adapt to a wide range of new tasks and environments, without forgetting what they have learned before – something that humans and animals seem to do naturally during their lifetime. This course will focus on the rapidly growing research area of machine learning called continual lifelong learning which aims to push modern AI from “narrow” to “broad”, i.e. to develop learning models and algorithms capable of never-ending, lifelong, continual learning over a large, and potentially infinite set of drastically different tasks and environments. In this course, we will review state-of-art literature on continual lifelong learning in modern AI, including catastrophic forgetting problem and recent approaches to overcoming it in deep neural networks, from augmenting stochastic gradient decent algorithm to alternative optimization approaches, architecture adaptation/evolution based on expansion/compression, dynamic routing/selective execution (“internal” attention) and other approaches; moreover, we will also survey related work on stability vs plasticity dilemma in neuroscience and related topics in biology of adaptation and memory. | 4 | TBD | TBD |
| Aaron Courville | IFT6759 – Professional Master | Preparation for practical applications of machine learning through concrete projects on real data use of specialized machine learning software for artificial intelligence Note: It is recommended to take IFT6135 Representation Learning before or concomitant. | 4 | Wed. 4:30 – 6:30 Fri. 9:30 – 11:30 | 08-01-2021 – 16-04-2021 |
| Will Hamilton | COMP 766 – Advanced Topics: Applications 1(Winter 2020) | Graph representation learning (GRL) is a quickly growing subfield of machine learning that seeks to apply machine learning methods to graph-structured data. Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. This course will provide an introduction to graph representation learning, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks. During the course, we will study both the theoretical motivations and practical applications of these methods. | 4 | TBD | TBD |
| Guillaume Lajoie | MAT6215 Dynamical Systems | This graduate course is an introduction to the treatment of nonlinear differential equations, and more generally to the theory of dynamical systems. The objective is to introduce the student to the theory of dynamical systems and its applications. Firstly, classical dynamics analysis techniques will be presented: continuous and discrete flows, existence and stability of solutions, invariant manifolds, bifurcations and normal forms. Secondly, an introduction to ergodic theory will be presented: chaotic dynamics, strange attractors, dynamic entropy, high-dimensional systems (e.g. networks), driven dynamics and information processing. Particular attention will be paid to computations performed by dynamical systems. Throughout the course, there will be an emphasis on modern applications in neuroscience, artificial intelligence, and data-driven modeling. This inlcudes: dynamical systems tools for optimization, network dynamics and links to deep learning & representation theory, computational neuroscience tools. At the end of the course, the student will be able to apply dynamical systems analysis techniques to concrete problems, as well as navigate the modern dynamical systems literature. Several examples and applications making use of numerical simulations will be used. To take this course, the student must master, at an undergraduate level, notions of calculus, linear differential equations, linear algebra and probability. | 3 | Tue. 9:30 – 1:00 (subject to changes) | TBD |
| Blake Richards | COMP 596 – Topics in Computer Science 3 | This is a historical overview of the influence of neuroscience on artificial intelligence. It will be a seminar style class, mixing lecture, discussion, and class presentations. Topic covered will include perceptrons, the origins of reinforcement learning, parallel distributed processing, Boltzmann machines, brain inspired neural network architectures, and modern approaches to deep learning that incorporate attention, memory and ensembles. | 3 | TBD | TBD |
| Gauthier Gidel | IFT 6756 – Game Theory and ML course | The number of Machine Learning applications related to game theory has been growing in the last couple of years. For example, two-player zero-sum games are important for generative modeling (GANs) and mastering games like Go or Poker via self-play. This course is at the interface between game theory, optimization, and machine learning. It tries to understand how to learn models to play games. It will start with some quick notions of game theory to eventually delve into machine learning problems with game formulations such as GANs or Multi-agent RL. This course will also cover the optimization (a.k.a training) of such machine learning games. | 4 | Tue. 4:30 – 6:30 Fri. 1:30 – 3:30 | 12-01-2020 30-04-2020 |
| Jian Tang | MATH 80600A – Machine Learning II: Deep Learning and Applications (Winter 2020) | Deep learning has achieved great success in a variety of fields such as speech recognition, image understanding, and natural language understanding. This course aims to introduce the basic techniques of deep learning and recent progress of deep learning on natural language understanding and graph analysis. This course aims to introduce the basic techniques of deep learning including feedforward neural networks, convolutional neural networks, and recurrent neural networks. We will also cover recent progress on deep generative models. Finally, we will introduce how to apply these techniques to natural language understanding and graph analysis. | 3 | TBD | TBD |
| Siamak Ravanbakhsh | COMP767-002 Probabilistic Graphical Models | The course covers representation, inference and learning with graphical models; the topics at high level include directed and undirected graphical models; exact inference; approximate inference using deterministic optimization based methods, as well as stochastic sampling based methods; learning with complete and partial observations. | 4 | Tue. 10 – 11:30 Thu. 10 – 11:30 | TBD |
| Reihaneh Rabbany | COMP 551 – Applied Machine Learning (Winter 2020) | This course covers a selected set of topics in machine learning and data mining, with an emphasis on good methods and practices for deployment of real systems. The majority of sections are related to commonly used supervised learning techniques, and to a lesser degree unsupervised methods. This includes fundamentals of algorithms on linear and logistic regression, decision trees, support vector machines, clustering, neural networks, as well as key techniques for feature selection and dimensionality reduction, error estimation and empirical validation. | 4 | TBD | TBD |
| Emma Frejinger | IFT-6521 – Programmation dynamique (Winter 2019) | This course aims to study algorithms and mathematical tools used to analyze or optimize sequential decision processes, for which there is interaction between decisions, in a certain or uncertain environment. We will see how to implement the calculation algorithms and we will study their performance. In several cases we will be able to demonstrate certain properties characterizing the form of an optimal policy. Examples of applications from different areas, including management and finance, will also be examined. | 4 | TBD | TBD |
| Tim O’Donnell | LING 683 – Probabilistic Programming | An introduction to Bayesian inference via probabilistic programming. | TBD | Thurs. 8:30 – 10:00 | TBD |
| Sarath Chandar | INF6900A/INF7900 – Scientific and Technical Communication | TBD | TBD | TBD | TBD |
Courses and schedules - Fall 2020 (preliminary list)
| Professor | Course | Description | Credits | Schedule | Dates |
|---|---|---|---|---|---|
| Simon Lacoste-Julien | IFT 6269 – Modèles Graphiques probabilistes et apprentissage | System Representation as probabilistic graphical models, inference in graphical models, learning parameters from data. | 4 | Tue. 2:30 – 4:30 Fri. 1:30 – 3:30 | 09-01-2020 – 12-08-2020 |
| Ioannis Mitliagkas | IFT 6390 – Fondements de l’Apprentissage Machine | Basic elements of statistical and symbolic learning algorithms. Examples of applications in data mining, pattern recognition, nonlinear regression, and time data. | 4 | Section A Wed. 9:30 – 11:30 Thu. 9:30 – 10:30 Section A1 Thu. 10:30 – 12:30 Section A102 Thu. 10:30 – 12:30 | 09-02-2020 – 12-03-2020
|
| Laurent Charlin | MATH 80629A Machine Learning l : Large-Scale Data Analysis and Decision Making | In this course, we will study machine learning models. In addition to standard models, we will study models for analyzing user behaviour and for decision making. Massive datasets are now common and require scalable analysis tools. Machine learning provides such tools and is widely used for modelling problems across many fields including artificial intelligence, bioinformatics, finance, marketing, education, transportation, and health. In this context, we study how standard machine learning models for supervised (classification, regression) and unsupervised learning (for example, clustering and topic modelling) can be scaled to massive datasets using modern computation techniques (for example, computer clusters). In addition, we will discuss recent models for recommender systems as well as for decision making (including multi-arm bandits and reinforcement learning). | 3 | Mon. 8:30 – 11:30 | 09-07-2020 – 12-07-2020 |
| Laurent Charlin | MATH 80629 Apprentissage automatique I : Analyse des Mégadonnées et Prise de décision | In this course, we will study models of machine learning. Furthermore, we will also study models of user behavior analysis and decision making. Large datasets are now comMon. and require scalable analytics. In addition, we will discuss recent models for referral systems as well as for decision-making (including multi-armed bandits and reinforcement learning). | 3 | Fri. 8:30 – 11:30 | 09-04-2020 – 12-04-2020 |
| Jackie C. K. Cheung | COMP 550 – Natural Language Processing | An introduction to the computational modelling of natural language, including algorithms, formalisms, and applications. Computational morphology, language modelling, syntactic parsing, lexical and compositional semantics, and discourse analysis. Selected applications such as automatic summarization, machine translation, and speech processing. Machine learning techniques for natural language processing.
| 3 | TBA | TBA
|
| Siva Reddy, Timothy J. O’Donnell | COMP 596 — From Natural Language to Data Science | This course is for people with no experience is NLP and would like to see how it can be used for exciting data science applications. We suggest other NLP/CL courses if you want to focus on theoretical side of NLP/CL. Topics covered in this course include: Language data and applications, Searching through data, How to make sense of data, Language Modeling, Language to decisions, Information Retrieval, Information Extraction, Social Networks (Twitter and Facebook data), Recommendation systems, Ethics | 4 | TBA | TBA |
| Timothy J. O’Donnell | LING 645: Computational Linguistics | Introduction to foundational ideas in computational linguistics and natural language processing. Topics include formal language theory, probability theory, estimation and inference, and recursively defined models of language structure. Emphasis on both the mathematical foundations of the field as well as how to use these tools to understand human language. | TBA | TBA | TBA |
| Siamak Ravanbakhsh | COMP 551- Applied Machine Learning | The course will cover selected topics and new developments in data mining and applied machine learning, with a particular emphasis on good methods and practices for effective deployment of real systems. We will study commonly used algorithms and techniques, including linear and logistic regression, clustering, neural networks, support vector machines, decision trees and more. We will also discuss methods to address practical issues such as empirical validation, feature selection, dimensionality reduction, and error estimation. | 4 | Tue. 10:00 – 11:30 Thu. 10:00 – 11:30 | TBA |
| Reihaney Rabbany | COMP 596 – Network Science | An introduction to Network Science, this is a half lecture half seminar course. Networks model the relationships in complex systems, from hyperlinks between web pages, and co-authorships between research scholars to biological interactions between proteins and genes, and synaptic links between neurons. Network Science is an interdisciplinary research area involving researchers from Physics, Computer Science, Sociology, Math and Statistics, with applications in a wide range of domains including Biology, Medicine, Political Science, Marketing, Ecology, Criminology, etc. In this course, we will cover the basic concepts and techniques used in Network Science, review the state of the art techniques, and discuss the most recent developments. | 3 | TBA | TBA
|
| Liam Paull | IFT 6757 – Véhicule Autonomes | This course covers autonomous vehicle control with computer vision and machine learning. The course is “hands-on” and the students will receive a small-scale autonomous vehicle for the semester; Specific topics covered include sensors, vision, state estimation, navigation, planning, control and actuation. | 3 | TBA | TBA |
| Guy Wolf | MAT 6493 – Geometric data analysis | Formal and analytic approaches for modeling intrinsic geometries in data. Algorithms for constructing and utilizing such geometries in machine learning. Applications in classification, clustering, and dimensionality reduction. The course will accommodate anglophone students who do not speak French, as well as francophone students. | 4 | TBA | TBA |
| Sarath Chandar | INF8953CE – Machine Learning | This course provides a rigorous introduction to the field of machine learning (ML). The aim of the course is not just to teach how to use ML algorithms but also to explain why, how, and when these algorithms work. The course introduces fundamental algorithms in supervised learning and unsupervised learning from the first principles. The course, while covering several problems in machine learning like regression, classification, representation learning, dimensionality reduction, will introduce the core theory, which unifies all the algorithms. | 3 | TBA | TBA |
| Andrea Lodi | MTH6404 – Integer Programming | The course covers Mixed-Integer Linear Programming (MILP) technology. We start with an introduction on the basic concepts and building blocks of MILP solvers. Then, the core part of the course focuses on the modeling of basic combinatorial optimization problems by means of MILP and on the discussion on what a good model is and can be built. Such modeling concepts depend on the way the MILP is solved, i.e., by means of a well-designed (and hopefully short) sequence of calls to a Linear Programming general-purpose solver, the basic component of MILP software. The second part of the course focuses, instead, on the algorithms for treating models with exponentially-many rows or columns, which are shown in the previous part to play a fundamental role in MILP. Finally, the course ends by taking a step on the computational aspects of the MILP software. | TBA | TBA | TBA |
| Pierre-Luc Bacon | IFT6760C – Reinforcement Learning and Optimal Control | Markov Decision Processes, LP formulation, occupation measure, smooth bellman equations, projected bellman equations, analysis of TD algorithms, derivative estimation, discrete and continuous optimal control, Pontryagin maximum principle, single shooting, multiple shooting, collocation methods, inverse and meta reinforcement learning | TBA | Wed. 1:30 – 3:30 Mon. 3:30 – 5:30 | 09-02-2020 – 12-02-2020 |
| Aaron Courville | IFT 6268 – Self-supervised representation learning | There has been a great deal of recent progress on representation learning. Most of it coming in the form of “self-supervised” representation learning. In this course, we will take a fairly broad interpretation of what constitutes self-supervised methods and include some unsupervised and supervised learning methods when appropriate. We are interested in methods that learn effective semantic representations without (exclusively) relying on labeled data. More specifically, we will be interested in methods such as: Data augmentation tasks, Knowledge distillation, Self-distillation, Iterative learning, Contrastive methods (DIM, CPC, MoCo, SimCLR, etc), BYOL, and the analysis of these self-supervised methods. Our goal will be to gain an understanding how these methods work and what fundamental principles are at play. This is an advanced seminar course on the topic and as such, we will read and discuss a wide array of recent and classic papers. Lectures will be largely student lead. We assume knowledge of the fundamentals of machine learning (and in particular deep learning — as you would find in IFT6135), we will also explore applications of self-supervised representation learning to a wide range of domains, including Natural Language Processing, Computer Vision and Reinforcement Learning. Basic knowledge of these domains will also be assumed. Student evaluation will be done based on two components: 50% for class presentations (approx. 3 per student); and 50% for a course project. | 4 | Tue. 4:30 – 6:30 Thu. 6:30 – 8:30 | TBA |
Courses and schedules - Winter 2020
| Professor | Course | Description | Credits | Schedule | Dates |
|---|---|---|---|---|---|
| Simon Lacoste-Julien | IFT 6132 -Advanced Structures Prediction and Optimization | Advanced topics for prediction of structured objects (such as graphs, couplings, flow networks). Generative learning vs. discriminative. Energy models. Conditional random fields. Structured and latent variable SVM, CCCP algorithms. Large-scale optimization: Frank-Wolfe, reduced variance SGD, block-coordinate methods. Learning to search. RNN. Combinatorial algorithms: min-cost networks, sub-modular optimization, dynamic programming. | 4 | Tue. 2:30 – 4:30 Thu.1:30 – 3:30 | 07-01-2020 – 11-04-2020 |
| Aaron Courville | IFT 6135 – Apprentissage de représentations (Winter 2019) | Advanced topics in learning algorithms: deep architectures, neural networks and unsupervised probabilistic models. | 4 | Mon. 9:30 – 11:30 Wed. 12:30 – 2:30 | 07-01-2019 – 10-04-2019 |
| Ioannis Mitliagkas | IFT-6085 – Theoretical principles for deep learning | Research in deep learning produces state-of-the-art results on a number of machine learning tasks. Most of those advances are driven by intuition and massive exploration through trial and error. As a result, theory is currently lagging behind practice. The ML community does not fully understand why the best methods work. Why can we reliably optimize non-convex objectives? How expressive are our architectures, in terms of the hypothesis class they describe? Why do some of our most complex models generalize to unseen examples when we use datasets orders of magnitude smaller than what the classic statistical learning theory deems sufficient? A symptom of this lack of understanding is that deep learning methods largely lack guarantees and interpretability, two necessary properties for mission-critical applications. More importantly, a solid theoretical foundation can aid the design of a new generation of efficient methods—sans the need for blind trial-and-error-based exploration. In this class we will go over a number of recent publications that attempt to shed light onto these questions. Before discussing the new results in each paper we will first introduce the necessary fundamental tools from optimization, statistics, information theory and statistical mechanics. The purpose of this class is to get students engaged with new research in the area. To that end, the majority of credit will be given for a class project report and presentation on a relevant topic. Note: This is an advanced class designed for PhD students with serious mathematical background. | 4 | Wed. 9:30 – 11:30 Thu. 9:00 – 11:00 | 08-01-2020 – 16-04-2020 |
| Guillaume Rabusseau | IFT-6760a – Séminaire en apprentissage automatique | This course will give an overview of linear/multilinear algebra techniques for designing/analyzing ML algorithms and models, and engage students with new research in the area. – Fundamental notions of linear and multilinear algebra. – ML methods leveraging matrix/tensor decomposition: PCA/CCA, collaborative filtering, spectral graph clustering, spectral methods for HMM, K-FAC, spectral normalization, tensor method of moments, NN/MRF compression, tensor completion, etc. – Open problems. | 4 | Tue. 12:30 – 2:30 Thu. 11:30 – 1:30 | 07-01-2020 – 16-04-2020 |
| Irina Rish | IFT 6760b – Continual Learning: Towards “Broad” AI | Stephen Hawking famously said, ‘Intelligence is the ability to adapt to change.’ While today’s AI systems can achieve impressive performance in specific tasks, from accurate image recognition to super-human performance in games such as Go and chess, they are still quite “narrow”, i.e. not being able to easily adapt to a wide range of new tasks and environments, without forgetting what they have learned before – something that humans and animals seem to do naturally during their lifetime. This course will focus on the rapidly growing research area of machine learning called continual lifelong learning which aims to push modern AI from “narrow” to “broad”, i.e. to develop learning models and algorithms capable of never-ending, lifelong, continual learning over a large, and potentially infinite set of drastically different tasks and environments. In this course, we will review state-of-art literature on continual lifelong learning in modern AI, including catastrophic forgetting problem and recent approaches to overcoming it in deep neural networks, from augmenting stochastic gradient decent algorithm to alternative optimization approaches, architecture adaptation/evolution based on expansion/compression, dynamic routing/selective execution (“internal” attention) and other approaches; moreover, we will also survey related work on stability vs plasticity dilemma in neuroscience and related topics in biology of adaptation and memory. | 4 | Mon. 3:30 – 5:30 Thu. 4:30 – 6:30 | 06-01-2020 – 16-04-2020 |
| Pierre-Luc Bacon | IFT 6760C – Reinforcement Learning | Advanced course in reinforcement learning. Topics: Policy gradient methods, gradient estimation, analysis of valued-based function approximation methods, optimal control and automatic differentiation, bilevel optimization in meta-learning and inverse reinforcement learning. | 4 | Tue. 9:30 – 11:30 Fri. 1:30 – 3:30 | TBD |
| Aaron Courville | IFT6759 – Professional Master | Preparation for practical applications of machine learning through concrete projects on real data use of specialized machine learning software for artificial intelligence Note: It is recommended to take IFT6135 Representation Learning before or concomitant. | 4 | Wed. 2:30 – 4:30 Fri. 9:30 – 11:30 | TBD |
| Will Hamilton | COMP 766 – Advanced Topics: Applications 1(Winter 2020) | Graph representation learning (GRL) is a quickly growing subfield of machine learning that seeks to apply machine learning methods to graph-structured data. Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. This course will provide an introduction to graph representation learning, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks. During the course, we will study both the theoretical motivations and practical applications of these methods. | 4 | TBD | TBD |
| Doina Precup | COMP 767 – Advanced Topics: Applications 2 | Computer Science (Sci) : Advanced topics in computing systems. | 4 | Mon. 8:30-10:00 Wed. 8:30 – 10:00 | TBD |
| Guillaume Lajoie | MAT6115 Dynamical Systems | Introduction to nonlinear differential equations, classical techniques for dynamics analysis, discrete and continuous flows, existence and stability of solutions, invariant manifolds, bifurcations and normal forms, ergodic theory and chaos. The course will focus on modern applications of Dynamical Systems theory, including: optimization dynamics, recurrent network dynamics, computational neuroscience. | 3 | Tue. 9:30 – 12:30 | 07-01-2020 – 28-04-2020 |
| Blake Richards | COMP 596 – Topics in Computer Science 3 | This is a historical overview of the influence of neuroscience on artificial intelligence. It will be a seminar style class, mixing lecture, discussion, and class presentations. Topic covered will include perceptrons, the origins of reinforcement learning, parallel distributed processing, Boltzmann machines, brain inspired neural network architectures, and modern approaches to deep learning that incorporate attention, memory and ensembles. | 3 | Tue. 1:00 – 2:30 Thu. 1:00 – 2:30 | 07-01-2020 – 9-04-2020 |
| Siva Reddy | COMP 764 Advanced Topics Systems 1 | The field of natural language processing (NLP) has seen multiple paradigm shifts over decades, from symbolic AI to statistical methods to deep learning. We review this shift through the lens of natural language understanding (NLU), a branch of NLP that deals with “meaning”. We start with what is meaning and what does it mean for a machine to understand language? We explore how to represent the meaning of words, phrases, sentences and discourse. We then dive into many useful NLU applications. Throughout the course, we take several concepts in NLU such as meaning or applications such as question answering, and study how the paradigm has shifted, what we gained with each paradigm shift, and what we lost? We will critically evaluate existing ideas and try to come up with new ideas that challenge existing limitations. We will particularly work on making deep learning models for language more robust. This is a seminar-style course, where the class as a whole will work together in running the course. In the first few lectures, I will provide an overview of NLU and highlight the challenges the field is facing. | 4 | Tue. 4:05 – 5:25 Thu. 4:05 – 5:25 | TBD |
| Jian Tang | MATH 80600A – Machine Learning II: Deep Learning and Applications | Deep learning has achieved great success in a variety of fields such as speech recognition, image understanding, and natural language understanding. This course aims to introduce the basic techniques of deep learning and recent progress of deep learning on natural language understanding and graph analysis. This course aims to introduce the basic techniques of deep learning including feedforward neural networks, convolutional neural networks, and recurrent neural networks. We will also cover recent progress on deep generative models. Finally, we will introduce how to apply these techniques to natural language understanding and graph analysis. | 3 | Thu. 8:30 – 11:30 Fri. 3h30 – 6:30 | 09-01-2020 – 18-04-2020 |
| Siamak Ravanbakhsh | COMP 551 – Applied Machine Learning | Deep learning has achieved great success in a variety of fields such as speech recognition, image understanding, and natural language understanding. This course aims to introduce the basic techniques of deep learning and recent progress of deep learning on natural This course covers a selected set of topics in machine learning and data mining, with an emphasis on good methods and practices for deployment of real systems. The majority of sections are related to commonly used supervised learning techniques, and to a lesser degree unsupervised methods. This includes fundamentals of algorithms on linear and logistic regression, decision trees, support vector machines, clustering, neural networks, as well as key techniques for feature selection and dimensionality reduction, error estimation and empirical validation. | 4 | Tue. 4:30 – 5:30 Thu. 4:30 – 5:30 | 07-01-2020 – 09-04-2020 |
| Reihaneh Rabbany | COMP 551 – Applied Machine Learning | This course covers a selected set of topics in machine learning and data mining, with an emphasis on good methods and practices for deployment of real systems. The majority of sections are related to commonly used supervised learning techniques, and to a lesser degree unsupervised methods. This includes fundamentals of algorithms on linear and logistic regression, decision trees, support vector machines, clustering, neural networks, as well as key techniques for feature selection and dimensionality reduction, error estimation and empirical validation. | 4 | TBD | TBD |
| Emma Frejinger | IFT-6521 – Programmation dynamique (Winter 2019) | This course aims to study algorithms and mathematical tools used to analyze or optimize sequential decision processes, for which there is interaction between decisions, in a certain or uncertain environment. We will see how to implement the calculation algorithms and we will study their performance. In several cases we will be able to demonstrate certain properties characterizing the form of an optimal policy. Examples of applications from different areas, including management and finance, will also be examined. | 4 | Mon. 1:30-3:30 Thu. 11:30-1:30 | n/a |
| Bernard Gendron | IFT 6551 – Programmation en nombres entiers (Winter 2019) | Ce cours vise, d’une part, à introduire l’étudiant à de nombreux problèmes d’optimisation pouvant être formulés à l’aide de variables entières et, d’autre part, à le familiariser avec les méthodes de la programmation en nombres entiers. Pour plus de détails, consultez le texte suivant, qui propose une synthèse des sujets traités. | 4 | Mon. 11:30 – 1:30 Tue. 10:30 – 12:30 |
Courses and schedules - Fall 2019
| Noms Professeurs | Cours/sigles | Descriptions | Crédits | Horaires | Dates |
|---|---|---|---|---|---|
| SiMon. Lacoste-Julien | IFT 6269 – Modèles Graphiques probabilistes et apprentissage | System Representation as probabilistic graphical models, inference in graphical models, learning parameters from data. | 4 | Tue. 2:30 – 4:30 Fri. 1:30 – 3:30 | 03-09-2019 – 06-12-2019 |
| Ioannis Mitliagkas | IFT 6390 – Fondements de l’Apprentissage Machine | Basic elements of statistical and symbolic learning algorithms. Examples of applications in data mining, pattern recognition, nonlinear regression, and time data. | 4 | Section A :Wed. 9:30-11:30 et Thu. 9:30-10:30 Section A1 Thu. 10:30-12:30 Section A102 Thu. 10:30-12:30 | 03-09-2019 – 05-12-2019 |
| Laurent Charlin | MATH 80629A Machine Learning l : Large-Scale Data Analysis and Decision Making | In this course, we will study models of machine learning. Furthermore, we will also study models of user behavior analysis and decision making. Large datasets are now comMon. and require scalable analytics. In addition, we will discuss recent models for referral systems as well as for decision-making (including multi-armed bandits and reinforcement learning). | 3 | Wed. 8:30 – 11:30 | 04-09-2019 – 04-12-2019 |
| Laurent Charlin | MATH 80629 Apprentissage automatique I : Analyse des Mégadonnées et Prise de décision | In this course, we will study models of machine learning. Furthermore, we will also study models of user behavior analysis and decision making. Large datasets are now comMon. and require scalable analytics. In addition, we will discuss recent models for referral systems as well as for decision-making (including multi-armed bandits and reinforcement learning). | 3 | Thu. 8:30 – 11:30 | 05-09-2019 – 05-12-2019 |
| Jackie C. K. Cheung | COMP 550 – Natural Language Processing | An introduction to the computational modelling of natural language, including algorithms, formalisms, and applications. Computational morphology, language modelling, syntactic parsing, lexical and compositional semantics, and discourse analysis. Selected applications such as automatic summarization, machine translation, and speech processing. Machine learning techniques for natural language processing. | 3 | Tue. 11:35 – 12:55 Thu. 11:35 – 12:55 | 03-09-2019 -10-12-2019 |
| William L. Hamilton | COMP 551- Applied Machine Learning | The course will cover selected topics and new developments in data mining and applied machine learning, with a particular emphasis on good methods and practices for effective deployment of real systems. We will study commonly used algorithms and techniques, including linear and logistic regression, clustering, neural networks, support vector machines, decision trees and more. We will also discuss methods to address practical issues such as empirical validation, feature selection, dimensionality reduction, and error estimation. | 3 | Mon. 4:00 – 5:30 Wed. 4:00 – 5:30 | 06-09-2019 – 06-12-2019 |
| Rabbany Reihaney | COMP 596 – Network Science | Networks model the relationships in complex systems, from hyperlinks between web pages, and co-authorships between research scholars to biological interactions between proteins and genes, and synaptic links between neurons. | 3 | Tue. 10:00 – 11:30 Thu. 10:00 – 11:30 | 03-09-2019 – 09-12-2019 |
| Liam Paull | IFT 6757 – Véhicule Autonomes | 3 | Mon. 10:30 – 12:30 Wed. 11:30 – 1:30 | 02-09-2019 – 04-12-2019 | |
| Guy Wolf | MAT 6480W / STT 6705V – Special Topics in Geometric Data Analysis | 3 | Wed. 3:30 – 5:00 Thu.3:30 – 5:00 | 04-09-2019 – 04-12-2019 |
Courses and schedules - Winter 2019
| Professor | Course | Description | Credits | Schedule | Dates |
|---|---|---|---|---|---|
| Lacoste-Julien Simon | IFT 6132 -Advanced Structures Prediction and Optimization | Advanced topics for prediction of structured objects (such as graphs, couplings, flow networks). Generative learning vs. discriminative. Energy models. Conditional random fields. Structured and latent variable SVM, CCCP algorithms. Large-scale optimization: Frank-Wolfe, reduced variance SGD, block-coordinate methods. Learn to search. NNI. algorithms combinatorics: cost-min networks, sub-modular optimization, dynamic programming. | 4 | Tue. 2:30 – 14:30 Thu. 1:30 – 3:30 | 08-01-2018 – 12-04-2019 |
| Courville Aaron | IFT 6135 – Apprentissage de représentations | Advanced topics in learning algorithms: deep architectures, neural networks and unsupervised probabilistic models. | 4 | Mon. 9:30 – 11:30 Wed. 12:30 – 2:30 | 07-01-2019 – 10-04-2019 |
| Mitliagkas Ioannis | IFT-6085 – Theoretical principles for deep learning | This course consists of an overview of the most recent theoretical publications on deep learning. For each selected publication, Dr. Mitliagkas will introduce the theoretical concepts necessary to understand the scientific approach of the authors, but also the results presented. Several topics will be covered, such as the optimization of nonconvex functions and information theory. Since the main objective of this course is to introduce participants to new research in this area, the main evaluation of this course will be in the form of a research project. | 4 | Wed. 9:30 – 11:30 Thu. 9:00 – 11:30 | 09-01-2019 – 11-04-2019 |
| Rabusseau Guillaume | IFT-6760a – Séminaire en apprentissage automatique | This course will give an overview of linear/multilinear algebra techniques for designing/analyzing ML algorithms and models, and engage students with new research in the area. – Fundamental notions of linear and multilinear algebra. – ML methods leveraging matrix/tensor decomposition: PCA/CCA, collaborative filtering, spectral graph clustering, spectral methods for HMM, K-FAC, spectral normalization, tensor method of moments, NN/MRF compression, tensor completion, etc. – Open problems. | 4 | Tue. 12:30 – 2:30 Thu. 11:30 – 1:30 | 08-01-2019 – 12-04-2019 |
| Frejinger Emma | IFT-6521 – Programmation dynamique | This course aims to study algorithms and mathematical tools used to analyze or optimize sequential decision processes, for which there is interaction between decisions, in a certain or uncertain environment. We will see how to implement the calculation algorithms and we will study their performance. In several cases we will be able to demonstrate certain properties characterizing the form of an optimal policy. Examples of applications from different areas, including management and finance, will also be examined. | 4 | Mon. 1:30-3:30 Thu. 11:30-1:30 | n/a |
| Tang Jian | 6-600-18A – Data Mining Techniques | This course aims to introduce the basic techniques of data mining and their applications to different types of real-world data including transaction data, text data, and set data. | 3 | Fri. 6:30 – 9:30 | 11-01-2019 – 12-04-2019 |
| Gendron Bernard | IFT 6551 – Programmation en nombres entiers | Ce cours vise, d’une part, à introduire l’étudiant à de nombreux problèmes d’optimisation pouvant être formulés à l’aide de variables entières et, d’autre part, à le familiariser avec les méthodes de la programmation en nombres entiers. Pour plus de détails, consultez le texte suivant, qui propose une synthèse des sujets traités. | 4 | Mon. 11:30 – 1:30 Tue. 10:30 – 12:30 | |
Courses and schedules - Fall 2018
| Professor Names | Course | Descriptions | Credits | Hours | Dates |
|---|---|---|---|---|---|
| Ioannis Mitliagkas | IFT 6390 – Fundamentals of Machine Learning (Graduate) | This course is given in English. Basics of statistical and symbolic learning algorithms. Examples of applications in data mining, pattern recognition, nonlinear regression, and temporal data. | 4 | Wed 9:30 – 11:30 Lect Th 9:30 – 10:30 Lect Th 10:30 – 12:30 Lab | 2018-09-05 – 2018-12-06 |
| Lacoste-Julien Simon | IFT 6269 – Probabilistic graphical models and learning | Representing systems as graphical probabilistic models, inference in graphical models, learning parameters from data. | 4 | Tue 14:30 – 16:30 Sem Fri 13:30 – 15:30 Sem | 2018-09-04 – 2018-12-07 |
| Paull Liam | IFT 6757-Autonomous Vehicles | Problems in perception, navigation, and control, and their systems-level integration in the context of self-driving vehicles through an open-source curriculum for autonomy education (Duckietown) that emphasizes hands-on experience | 4 | Mon. 10:30 – 12:30 Wed. 11:30 – 1:30 | 05/09/2018 – 05/12/2018 |
| Guillaume Rabusseau | IFT3395 Fundamentals of Machine Learning (Under Graduate) | This course is given in French. Basics of statistical and symbolic learning algorithms. Examples of applications in data mining, pattern recognition, nonlinear regression, and temporal data. | 3 | Wed 9:30 – 11:30 Lect Th 9:30 – 10:30 Lect Th 10:30 – 12:30 Lab | 2018-09-05 – 2018-12-06 |
| Cheung Jackie | Comp 550 (McGill)- Natural Language Processing | An introduction to the computational modelling of natural language, including algorithms, formalisms, and applications. Computational morphology, language modelling, syntactic parsing, lexical and compositional semantics, and discourse analysis. Selected applications such as automatic summarization, machine translation, and speech processing. Machine learning techniques for natural language processing. | 3 | 2:35 PM – 3:55 PM TR ENGMC 13 | n/a |
| Lodi Andrea | MTH6404 (Poly)- Integer Programming | Course is given in English in Fall and French in Winter. Branch-and-bound: enumeration trees, exploration strategy, branching rules. Polyhedral theory: valid inequalities, dimensions. Unimodularity. Method of intersecting planes. Chvátal-Gomory cuts. Dantzig-Wolfe, column generation, Benders decompositions. Lagrangian relaxation. Backpack and courrier problems. | 3 | n/a | n/a |
| Charlin Laurent | 6-602-07 (HEC)- Applied multidimensional analysis | Data mining, factorial analysis, selecting variables and models, logistic regression, clustering, survival analysis, missing data | 3 | Mon. 12:00-15:00 Lect | n/a |
| Charlin Laurent | 80-629-17A (HEC) – Machine Learning for Large-Scale Data Analysis & Decision Making | Machine learning models for supervised (classification, regression) and unsupervised learning (for example, clustering and topic modelling) scaled to massive datasets using modern computation techniques (for example, computer clusters). | 3 | Wed 8:30-11:30 Lect | n/a |
| Alain Tapp | Data Science (IFT3700/IFT6700) | Contextualization and applications of probabilities, statistics, optimization and computer tools for data science; cleaning and visualization of data; statistical issues of machine learning on structured data. | n/a | Mon. 9:30 – 10:30 Tue. 12:30-14:30 Mon. 10:30-12:30 | 9-10-2018 – 03-12-2018 |
| Guillaume Lajoie | Dynamical Systems (MAT6115) | Introduction to the treatment of nonlinear differential equations, classical dynamics analysis techniques, continuous and discrete flows, existence and stability of solutions, invariant manifolds, bifurcations and normal forms, an introduction to ergodic theory and an overview of modern applications. | 3 | Tue. 10:30-12:00 Thu. 10:30-12:00 | 04/09/2018 – 20/12/2018 |
Courses and schedules - Winter 2018
| Noms Professeurs | Cours/sigles | Descriptions | Crédits | Horaires | Dates |
|---|---|---|---|---|---|
| Lacoste-Julien Simon | IFT 6132 – Advanced Structured Prediction and Optimization | Advanced topics for prediction of structured objects (such as: graphs, matching, network flows). Gernative vs. discriminative learning continuum. Energy-based models & surrogate losses. Conditional random field (CRF). Structured SVM. Latent variable structured SVM, CCCP algorithm. Large-scale optimization: Frank-Wolfe, variance-reduced SGD, block-coordinate methods. Learning to search. RNN. Combinatorial algorithms: min-cost network flow, submodular optimization, dynamic programs. | 4 | Tue. 14:30 – 17:30 Fri. 14:30 – 16:30 | 23-01-2018 – 30-04-2018 |
| Courville Aaron | IFT 6135 – Learning Representations | Advanced subjects in learning algorithms: deep architectures, neural networks and non-supervised probabilistic models. | 4 | Mon. 09:30 – 11:30 Wed. 12:30 – 14:30 | 08-01-2018 – 30-04-2018 |
| Pal Christopher | INF 8225 (Poly) – Probabilistic techniques and learning | Probabilistic methods in artificial intelligence. Bayesian networks, hidden Markov models, random Markov fields. Inference. Theory of statistical decisions and networks. Probabilistic treatment of natural language and visual perception. Recommendation systems, data mining, information search and computer vision. Deep learning and reinforcement learning. | 3 | Tue. 15:45 – 18:45 Thu. 13:45 – 16:45 | 08-01-2018 – 30-04-2018 |
| Precup Doina | COMP 767 (McGill) – Advanced Topics: Reinforcement learning | Advanced topics in reinforcement learning. | 4 | Tue. 4:00 – 5:30 PM Thu. 4:00 – 5:30 PM | 08-01-2018 – 16-04-2018 |
| Pineau Joelle | COMP 551 (McGill) – Applied Machine Learning | Clustering, neural networks, support vector machines, decision trees. Feature selection and dimensionality reduction, error estimation and empirical validation, algorithm design and parallelization, and handling of large data sets. | 4 | Tue. 11:35 AM – 12:55 PM Thu. 11:35 AM – 12:55 PM Mon. 8:35 AM – 9:55 AM Wed. : 8:35 AM – 9:55 AM | 08-01-2018 – 16-04-2018 |
| Ioannis Mitliagkas | IFT-6085 – Theoretical principles for deep learning | Overview of the most recent publications in the field of deep learning. Before discussing the new results in each paper, Dr. Mitliagkas will first introduce the necessary fundamental tools from optimization, statistics, information theory and statistical mechanics. The purpose of this class is to get students engaged with new research in the area. To that end, the majority of credit will be given for a class project report and presentation on a relevant topic. | 4 | Wed. 9:30 – 11:30 Thu. 9:00 – 11h00 | 08-01-2018 – 30-04-2018 |
| Alain Tapp | IFT 6271 – Sécurité informatique | Confidentiality and integrity of data with public and private key. Protection of TCP/IP layers; protection against computer parasites. User authentification methods. Evaluating and managing risks. | 3 | Mon. 09:30 – 11:30 Thu. 12:30 – 13:30 | 08-01-2018 – 30-04-2018 |
| Charlin Laurent | n/a | n/a | n/a | n/a | n/a |
| Bengio Yoshua | n/a | n/a | n/a | n/a | n/a |
| Vincent Pascal | n/a | n/a | n/a | n/a | n/a |
Courses and schedules - Fall 2017
| Noms Professeurs | Cours/sigles | Descriptions | Crédits | Horaires | Dates |
|---|---|---|---|---|---|
| Courville Aaron | IFT 3395/6390 – Fondamentals of Machine Learning | Basics of statistical and symbolic learning algorithms. Applications in data mining, pattern recognition, non-linear regression, time series data. | 4 | Wed. 9:30 – 11:30 Lect Thu. 9:30 – 10:30 Lect Thu. 10:30 – 12:30 Lab | 2017-09-06 – 2017-12-07 |
| Lacoste-Julien Simon | IFT 6269 – Probabilistic graphical models and learning | Representing systems as graphical probabilistic models, inference in graphical models, learning parameters from data. | 4 | Tue. 14:30 – 16:30 Sem Fri. 13:30 – 15:30 Sem | 2017-09-05 – 2017-12-08 |
| Paull Liam | IFT 6080 – Duckietown | Problems in perception, navigation, and control, and their systems-level integration in the context of self-driving vehicles through an open-source curriculum for autonomy education that emphasizes hands-on experience. | 4 | mon. 10:30 – 12:20 Cours Wed. 11:30-13:30 Cours | 2017-09-06 – 2017-12-06 |
| Pal Christopher | INF8702 (Poly) – Advanced Computer Graphics | Real-time rendering, polygonal and surface rendering. Textures. Parametric curves and surfaces. Local reflexion models. Illumination models. Volume rendering. Artistic rendering and virtual reality. | 3 | Tue. 9:30-12:30 Lab Fri. 12:45 – 15:45 Lect | |
| Precup Doina | COMP 652 (McGill) – Machine Learning | An overview of state-of-the-art algorithms used in machine learning, including theoretical properties and practical applications of these algorithms. | 4 | Mon. 14:35 – 15:55 Lect Wed. 14:35 – 15:55 Lect | 2017-09-05 – 2017-12-07 |
| Pineau Joelle | COMP 551 (McGill) – Applied Machine Learning | Clustering, neural networks, support vector machines, decision trees. Feature selection and dimensionality reduction, error estimation and empirical validation, algorithm design and parallelization, and handling of large data sets. | 4 | Mon. 13:05 – 14:25 Lect Wed. 08:35 – 9:55 Lect | 2017-09-05 – 2017-12-07 |
| Charlin Laurent | 6-602-07 (HEC)- Applied multidimensional analysis | Data mining, factorial analysis, selecting variables and models, logistic regression, grouping analysis, survival analysis, missing data | 3 | Thu. 18:45-21:45 Lect | n/a |
| 80-629-17A (HEC) – Machine Learning for Large-Scale Data Analysis & Decision Making | Machine learning models for supervised (classification, regression) and unsupervised learning (for example, clustering and topic modelling) scaled to massive datasets using modern computation techniques (for example, computer clusters). | 3 | Wed. 8:30-11:30 Lect | n/a | |
| Lodi Andrea | MTH6404 (Poly)- Integer Programming | Course given in English in Fall and French in Winter. Branch-and-bound: enumeration trees, exploration strategy, branching rules. Polyhedral theory: valid inequalities, dimensions. Unimodularity. Method of intersecting planes. Chvátal-Gomory cuts. Dantzig-Wolfe, column generation, Benders decompositions. Lagrangian relaxation. Backpack and courrier problems. | 3 | Tue. 12:45 – 15:45 Lect | n/a |
| Cheung Jackie | Comp 550 (McGill)- Natural Language Processing | An introduction to the computational modelling of natural language, including algorithms, formalisms, and applications. Computational morphology, language modelling, syntactic parsing, lexical and compositional semantics, and discourse analysis. Selected applications such as automatic summarization, machine translation, and speech processing. Machine learning techniques for natural language processing. | 3 | Tue. 16:05 – 17:25 Lect Thu. 16:05 – 17:25 Lect | 2017-09-05 – 2017-12-06 |
Courses and schedules - Summer 2017
| Professor | Course/Number | Descriptions | Credits | Schedule | Dates |
|---|---|---|---|---|---|
| Pal Christopher | INF6953H (Poly) – Deep Learning | Convolutional neural networks, autoencoders, recurrent neural networks, long short-term memory (LSTM) networks. Stochastic networks, conditional random fields, Boltzmann machines. Mixed stochastic and deterministic models. Deep reinforcement learning. | 3 | Tue. 13:00 – 16:00 Lect Wed. 13:00 – 16:00 Lab Thu. 13:00 – 16:00 Lect | 2017-05-07 – 2017-08-24 |
Courses and schedules - Winter 2017
| Professor | Course/Number | Descriptions | Credits | Schedule | Dates |
|---|---|---|---|---|---|
| Lacoste-Julien Simon | IFT 6085 – Advanced Structured Prediction | Energy-based models & surrogate losses. Generative learning / discriminative learning continuum. Conditional random field (CRF). Structured SVM. Latent variable structured SVM, CCCP algorithm. Large-scale optimization: Frank-Wolfe, variance-reduced SGD, block-coordinate methods. Learning to search. RNN. Combinatorial algorithms: min-cost network flow, submodular optimization, dynamic programs. | 4 | Wed. 10:30 – 12:30 Fri. 15:00 – 16:59 | 6 Jan to 12 Apr 2017 |
| Courville Aaron | IFT 6266 – Learning algorithms | Advanced subjects in learning algorithms: deep architectures, neural networks and non-supervised probabilistic models. | 4 | Mon. 14:30 – 16:30 Thu. 09:30 – 11:30 | 5 Jan to 13 Apr 2017 |
| Pal Christopher | INF 8225 (Poly) – Probabilistic techniques and learning | Probabilistic methods in artificial intelligence. Bayesian networks, hidden Markov models, random Markov fields. Inference. Theory of statistical decisions and networks. Probabilistic treatment of natural language and visual perception. Recommendation systems, data mining, information search and computer vision | 3 | Mon. 12h45 – 15h45 Lab Tue. 9h30 – 12h30 Lecture | |
| Precup Doina | COMP 652 (McGill) – Machine Learning | An overview of state-of-the-art algorithms used in machine learning, including theoretical properties and practical applications of these algorithms. | 4 | Tue. 13:05 – 14:25 Thu. 13:05 – 14:25 | 4 Jan to 11 Apr 2017 |
| COMP 767 (McGill) – Advanced Topics: Reinforcement learning | Advanced topics in reinforcement learning. | 4 | Fri. 10:05 – 12:55 | 4 Jan to 11 Apr 2017 | |
| Pineau Joelle | COMP 551 (McGill) – Applied Machine Learning | Clustering, neural networks, support vector machines, decision trees. Feature selection and dimensionality reduction, error estimation and empirical validation, algorithm design and parallelization, and handling of large data sets. | 4 | Tue. 13:05 – 14:25 Thu. 13:05 – 14:25 | 4 Jan to 11 Apr 2017 |
| Charlin Laurent | n/a | n/a | n/a | n/a | n/a |
| Bengio Yoshua | n/a | n/a | n/a | n/a | n/a |
| Vincent Pascal | n/a | n/a | n/a | n/a | n/a |
Courses and schedules - Fall 2016
| Professor | Course/Number | Descriptions | Credits | Schedule | Dates |
|---|---|---|---|---|---|
| Vincent Pascal | IFT 3395 – Fundamentals of machine learning (1st cycle) | Basic elements of statistical and symbolic learning algorithms. Applications in data mining, pattern recognition, nonlinear regression and time-series data. Note: Knowledge of numerical analysis recommend, such as in IFT 2425. | 3 | Wed. 09:30 – 11:30 Lecture Thu. 09:30 – 10:30 Lecture Thu. 10:30 – 12:30 LAB | 1 sept to 8 dec 2016 |
| IFT 6390 -Fundamentals of machine learning (2nd cycle) | Basic elements of statistical and symbolic learning algorithms. Applications in data mining, pattern recognition, nonlinear regression and time-series data. Note: Knowledge of numerical analysis recommend, such as in IFT 2425. | 4 | Wed. 09:30 – 11:30 Lecture Thu. 09:30 – 10:30 Lecture Thu. 10:30 – 12:30 LAB | 1 sept to 8 dec 2016 | |
| Lacoste-Julien Simon | IFT 6269 – Probabilistic graphical models and learning | Representing systems as graphical probabilistic models, inference in graphical models, learning parameters from data. | 4 | Tue. 14:30 – 16:30 Lecture Fri 13:30 – 15:30 Lecture | 2 sept to 6 dec 2016 |
| Charlin Laurent | 6-602-07 (HEC)- Applied multidimensional analysis | Data mining, factorial analysis, selecting variables and models, logistic regression, grouping analysis, survival analysis, missing data | 3 | Mon. 12:00 – 15:00 Lecture | 29 aug to 5 dec 2016 |
| Bengio Yoshua | n/a | n/a | n/a | n/a | n/a |
| Courville Aaron | n/a | n/a | n/a | n/a | n/a |
| Pal Christopher | n/a | n/a | n/a | n/a | n/a |
Thu.
