Pascal Poupart Courses

CS885 Reinforcement Learning - Spring 2020

Dive into advanced reinforcement learning techniques including trust region methods, maximum entropy approaches, and imitation learning strategies.

• YouTube
• 1 hour 55 minutes
• Self-Paced
• Free Video

Introduction to Machine Learning - Spring 2019 - University of Waterloo

Dive into comprehensive machine learning fundamentals covering neural networks, SVMs, deep learning, CNNs, transformers, and ensemble methods from University of Waterloo.

• YouTube
• 1 day 4 hours 26 minutes
• Self-Paced
• Free Video

Reinforcement Learning - Spring 2018

Master reinforcement learning algorithms that enable machines to learn from partial feedback, covering Markov processes, deep RL, bandits, and applications in robotics and games.

• YouTube
• 1 day 22 minutes
• Self-Paced
• Free Video

Inverse RL

Explores inverse reinforcement learning through feature matching, feature expectations, margin maximization, nonlinear rewards, optimization, and policy induction.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Distributional RL

Explore distributional reinforcement learning through return distributions, policy evaluation, Bellman equations, and C51.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Partially Observable Reinforcement Learning

A concise lecture on belief monitoring and recurrent networks for reinforcement learning in partially observable environments.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Imitation Learning

Explores imitation learning through behavioral cloning, GAIL, inverse dynamics, and applications in autonomous driving, conversational agents, and robotics.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Maximum Entropy Reinforcement Learning

A graduate lecture on maximum entropy reinforcement learning, covering stochastic policies, soft Q-learning, policy iteration, and Soft Actor-Critic.

• YouTube
• 42 minutes
• Self-Paced
• Free Video

Trust Region & Proximal Policy Optimization

Explains trust-region and proximal policy optimization for policy-gradient reinforcement learning, including KL-divergence constraints, derivations, algorithms, and empirical results.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

CS480-680 Lecture 19 - Attention and Transformer Networks

Lecture on attention mechanisms and transformer networks, including multihead attention, masking, recurrence, and normalization.

• YouTube
• 1 hour 23 minutes
• Self-Paced
• Free Video

CS480-680 - Hidden Markov Models

Explore Hidden Markov Models through monitoring, hindsight reasoning, most likely explanation, and robot localization applications.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

Convolutional Neural Networks

Learn how convolutional neural networks use convolutions, pooling, feature maps, and sparse connections for digit recognition and classification.

• YouTube
• 1 hour 15 minutes
• Self-Paced
• Free Video

Support Vector Machines

A compact lecture derives support vector machines through margin classifiers, distance measures, equivalent optimization, and the Lagrangian dual representation.

• YouTube
• 1 hour 18 minutes
• Self-Paced
• Free Video

Logistic Regression and Generalized Linear Models

Learn logistic regression and generalized linear models through the exponential family, Newton's method, classification, app recommendation, and sparsity.

• YouTube
• 1 hour 35 minutes
• Self-Paced
• Free Video

CS480-680 - K-Nearest Neighbours

Explore K-nearest neighbours for classification and regression, including accuracy, consistent hypotheses, and underfitting.

• YouTube
• 1 hour 29 minutes
• Self-Paced
• Free Video