The Minimal Series (name yet not determined) is a series of notebooks that take you from Andrej Karpathy’s Micrograd to writing and understanding other machine learning and reinforcement learning concepts. I’m hoping to write the cleanest code possible while helping you understand the underlying concepts.
General ML
RL
TODO:
- RNN
- CNN
- GRU
- LSTM
- Transformer
- Policy Gradient
- NEAT
- ES
- Autoencoders (VAE-varients)
- DIffusion
- GA
- Entropy which leads to KL divergence
- Ant Colony Optimization
- Simulated Annealing