This repository contains implementations of machine learning papers. In the early-works folder, there are fundamental algorithms, mostly derived from data science, that have been implemented from scratch in Python. Each implementation is accompanied by personal notes aimed at deeper understanding—although written primarily for myself, they may still be helpful to others.
0 - Basic Concepts of Statistics
- 1943-Logical-Calculus - McCulloch-Pitts Neuron Model
- 1949-The-Organization-Of-Behavior - Hebbian Learning
- 1958-The-Perceptron - Perceptron Algorithm
- 1960-Adaline-Madaline - Adaptive Linear Neuron and Multiple Adaptive Linear Neuron
- 1967-KNN - k-Nearest Neighbors Algorithm
- 1993-C4.5 - Decision Tree Algorithm
- K-Means
- Linear Regression
- Logistic Regression
- Naive Bayes
- PCA
- SVM
- CNN
- RNN-LSTM-GRU
- Diffusion Models
- DQN
- Hopfield Networks
- Boltzmann Machine
- Attention Mechanism - Encoder-Decoder
-
2020 - Learning Mesh-Based Simulation with Graph Networks
Already customized for blender dataset here
Reimplementation with PyTorch (planned)