Warrick's Machine Learning Notebook

Hi! Warrick here.

This documents my journey to learning ML.

This will be a combination of algorithms and algorithms learned from both my course work and side projects, with from scratch examples of code.

Introduction

1. Supervised and Unsupervised Learning!

Classical Machine Learning (Complete)

1. Decision Trees + Random Forest (Complete)

2. Linear Regression (Complete)

3. k-Nearest Neighbors (Complete)

4. Logistic Regression (Complete)

5. Naive Bayes (Complete)

Deep Learning

1. Artificial Neural Networks (Complete)

2. Convolutional Neural Networks (Complete)

3. Autoencoders and Unsupervised Learning (Complete)

4. RNNs, LSTMs, and GRUs (Complete)

5. Transformers (Complete)

6. GANs (Complete)

7. Graph Neural Networks and GCN (Complete)

Reinforcement Learning

1. Basics: State, Action, Value Functions (Complete)

2. Dynamic Programming and Bellman Equations (Complete)

3. Monte Carlo Policy Evaluation

4. SARSA

5. Q-Learning

6. RL-Squared (Y. Duan et al)

7. PPO (Proximal Policy Optimization)