Introduction to Deep Learning

Introduction to Deep Reinforcement Learning

Basics of Probability

Basics of Linear Algebra

Basics of Optimization

Linear models

Least squares method

Logistic regression

Generative and discriminative models

Linear regression as Maximum likelihood estimation

The Bayesian view

Bias-Variance decomposition

Maximum likelihood with latent variables – EM algorithm

K-means Clustering

PCA

Nonlinear models for classification and regression

Multilayer perceptions

Gradient descent on squared error loss

Backpropagation

automatic differentiation

Stochastic gradient descent

Optimization issues

Cross-entropy loss

Issues of Generalization

Convolutional Neural Networks

CNNs in computer vision

VGG net

Resnet

recurrent neural networks

Encoder-Decoder architectures

Transformers

Attention models

Deep Generative models

RBM

VAE

GAN

Multi-armed bandits

Markov decision processes

Examples

Numerical solutions

Monte-Carlo Algorithms for Prediction and Control

On-policy and Off-policy Algorithms

Temporal Difference Learning

Q-learning/SARSA/Expected SARSA Algorithms

Double Q-learning

Temporal Difference Learning with Function Approximation

Linear and Non-linear Function Approximation Architectures

Q-learning/SARSA/Double Q-Learning with Function Approximation

Policy Gradient Methods

REINFORCE Algorithm

Actor-critic Algorithms

Deep Value and Policy-based Algorithms

Deep Q-network Algorithm

Trust Region Policy Optimisation

Proximal Policy Optimisation

Asynchronous Advantage Actor Critic

Generalised Advantage Estimation Algorithm

Assignment 1: Linear regression and classification

Assignment 2: MLP using backpropagation

Assignment 3: Image classification using CNNs

Assignment 4: Value/policy iteration algorithms

Assignment 5: Monte-Carlo and temporal difference algorithms

Assignment 6: Stable baselines and hugging face

Capstone Projects

Python

Pytorch

Gym