Lectures related to Function approximation

Deep Learning: Data, Models, and Challenges

Provides an overview of deep learning concepts, focusing on data, model architecture, and challenges in handling large datasets.

Policy Gradient Methods: Binary Actor Example

Introduces policy gradient methods using a simple example of a single neuron with binary output.

Policy Gradient Methods in Reinforcement Learning

Covers policy gradient methods in reinforcement learning, focusing on optimization techniques and practical applications like the cartpole problem.

Deep Learning: No Free Lunch Theorem and Inductive Bias

Covers the No Free Lunch Theorem and the role of inductive bias in deep learning and reinforcement learning.

Nonlinear Supervised Learning

Explores the inductive bias of different nonlinear supervised learning methods and the challenges of hyper-parameter tuning.

Neural Networks: Learning Features & Linear Prediction

Explores neural networks' ability to learn features and make linear predictions, emphasizing the importance of data quantity for effective performance.

Policy Gradient Methods: Reinforcement Learning Techniques

Provides an overview of policy gradient methods in reinforcement learning, focusing on the log-likelihood trick and the transition from batch to online learning.

Replica computation and machine learning

Explores replica computation, algorithmic energy minimization, and their connection to machine learning concepts.

Introduction to Reinforcement Learning: Concepts and Applications

Introduces reinforcement learning, covering its concepts, applications, and key algorithms.

Deep and Robust Reinforcement Learning Techniques

Discusses advanced reinforcement learning techniques, focusing on deep and robust methods, including actor-critic frameworks and adversarial learning strategies.

Multi-layered Perceptron: History and Training Algorithm

Explores the historical development and training of multi-layered perceptrons, emphasizing the backpropagation algorithm and feature design.

Policy Gradient Methods: Direct Action Learning in Reinforcement Learning

Covers policy gradient methods, focusing on direct action learning and optimizing rewards in reinforcement learning.

Lagrange Interpolation: Numerical Integration Techniques

Covers Lagrange interpolation and its application in numerical integration techniques, focusing on both non-composite and composite methods of quadrature.