How uthmankontao/machine-learning works
This repository is a collection of machine-learning course materials and practical exercises, not a single application. A learner studies notebooks and implements or explores methods across statistical learning, reinforcement learning, and graph machine learning. The README highlights optimization, regularization, model selection, hyperparameter tuning, AutoML, representation learning, clustering, and factorization; the tree also documents graph algorithms and RL exercises. Sampled source confirms examples for bandits, grid-world planning, maze interaction, graph edit distance, and graph datasets. Many notebook details are unsampled, so their internal wiring is not inferred.
Main entry points: PART IV Graph Neural Networks · Maze_generating_interface.py Maze Design · ForTP3.py Maze RL Exercise · 1_Régression Linéaire Regression
Components 22
Statistical Learning
- Regression
ML_advanced/1_Régression Linéaire - LASSO
ML_advanced/2_Lasso - LASSO and Ridge
ML_advanced/3_Lasso_et_Ridge - Optimality Conditions
- Proximal Methods
ML_advanced/5_Lasso_proximal - Elastic Net
ML_advanced/TP8_ElasticNet - MMM Analysis
ML_advanced/MMM - Other ML Methods
ML_advanced
Reinforcement Learning
- Bandit Learning
ML_ReinforceLearning/TP1 - Markov Decision Processes
ML_ReinforceLearning/TP2 - Maze Design
ML_ReinforceLearning/TP3/Maze_generating_interface.py - Maze RL Exercise
ML_ReinforceLearning/TP3/ForTP3.py
Graph Learning
- Graph Introduction
ML_graphs/PART I/TP1_Introduction - Graph Algorithms
ML_graphs/PART I/TP2_Algorithms - Graph Morphisms
ML_graphs/PART I/TP3_Graphs_Morphisms - GED with LSAP
ML_graphs/PART II/1_Graph Edit Distance with LSAP - GED with A-star
ML_graphs/PART II/2_Astar - Graph Embeddings
ML_graphs/PART III - Graph Neural Networks
ML_graphs/PART IV - ZFR Dataset
ML_graphs/PART IV/TP_GNN_challenge_M2/ZFRdataset.py - Expressive Dataset
ML_graphs/PART IV/TP_graph_expressive/preparecounting.py
Other components
- Learner
Connections 22
- Learner → Regression: studies
- Learner → LASSO: studies
- Learner → LASSO and Ridge: studies
- Learner → Optimality Conditions: studies
- Learner → Proximal Methods: studies
- Learner → Elastic Net: studies
- Learner → MMM Analysis: explores
- Learner → Other ML Methods: explores
- Learner → Bandit Learning: studies
- Learner → Markov Decision Processes: studies
- Learner → Maze Design: designs maze
- Maze Design → Maze RL Exercise: provides maze
- Learner → Maze RL Exercise: explores
- Learner → Graph Introduction: studies
- Learner → Graph Algorithms: studies
- Learner → Graph Morphisms: studies
- Learner → GED with LSAP: implements
- Learner → GED with A-star: implements
- Learner → Graph Embeddings: studies
- Learner → Graph Neural Networks: studies
- Graph Neural Networks → ZFR Dataset: uses dataset
- Graph Neural Networks → Expressive Dataset: uses dataset