Simons Institute Courses

Towards Verified Deep Learning

Explore formal methods for verifying deep learning systems, focusing on robustness, semantic analysis, and applications in cyber-physical systems with UC Berkeley's Sanjit Seshia.

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

Reinforcement Learning via an Optimization Lens

Explore reinforcement learning through an optimization lens, covering MDPs, Bellman equations, and novel approaches to solving RL problems using linear programming and primal-dual formulations.

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

Reinforcement Learning in Recommender Systems - Some Challenges

Explore challenges in applying reinforcement learning to recommender systems, including scale, stochastic action sets, and user learning over long horizons. Gain insights on addressing these issues.

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

Off-Policy Policy Optimization

Explore advanced reinforcement learning techniques, focusing on off-policy optimization, batch methods, and sequential decision-making in deep learning contexts.

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

Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes

Explore policy gradient methods in Markov Decision Processes, covering optimality, approximation, and key concepts like entropy regularization and natural policy gradient.

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

On the Hardness of Reinforcement Learning With Value-Function Approximation

Explore challenges in reinforcement learning with value-function approximation, focusing on batch learning in large MDPs and the limitations of realizability assumptions.

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

Reinforcement Learning in Feature Space: Complexity and Regret

Explore reinforcement learning in feature space, focusing on complexity, regret analysis, and innovative approaches like MatrixRL. Learn about state feature mapping and its applications in real-world scenarios.

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

Flexible Neural Networks and the Frontiers of Meta-Learning

Explore cutting-edge approaches in meta-learning and flexible neural networks for rapid skill acquisition in AI agents, with applications in few-shot image classification and real-world scenarios.

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

Machine Learning-Based Design of Proteins and Small Molecules

Explore machine learning techniques for designing proteins and small molecules, covering directed evolution, model-based optimization, and challenges in deep learning applications.

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

Sample-Complexity of Estimating Convolutional and Recurrent Neural Networks

Explore sample-complexity in estimating neural networks, focusing on CNN and RNN architectures. Learn about generative models, minimax analysis, and key results through theoretical proofs and practical experiments.

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

Studying Generalization in Deep Learning via PAC-Bayes

Explore PAC-Bayes theory's application to deep learning generalization, focusing on risk bounds, optimal priors, and SGD prediction for neural networks.

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

Towards Understanding Transfer Learning with Applications to Medical Imaging

Explore transfer learning in medical imaging, focusing on deep learning applications, performance evaluation, and feature similarity analysis using CCA. Insights on ImageNet models and chest X-rays included.

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

Robust Deep Learning Under Distribution Shift

Explore deep learning challenges under distribution shift, covering adversarial attacks, label shift detection, and domain adaptation techniques for robust model performance in real-world scenarios.

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

Using Deep Learning for Perception in Autonomous Systems - A Perspective from Control Theory

Explore deep learning for perception in autonomous systems, focusing on efficient navigation using monocular RGB cameras in unknown environments. Control theory insights and practical lessons included.

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

Lessons Learned from Evaluating the Robustness of Defenses to Adversarial Examples

Explore robustness of AI defenses against adversarial examples, evaluating threat models and defense strategies to improve security in deep learning systems.

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