awesome-machine-learning
github.com/awesomelistsio/awesome-machine-learning ↗A curated list of awesome frameworks, libraries, tools, tutorials, datasets, and research papers in machine learning. This list covers a wide array of topics, from foundational algorithms to modern techniques in supervised, unsupervised, and reinforcement learning.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me reinforcement learning resources from awesome-machine-learning"
Installation instructions →What's inside
Reinforcement Learning
- Actor-Critic Methods
A family of reinforcement learning algorithms that use both policy and value functions.
- Deep Q-Network (DQN)
A deep learning approach for reinforcement learning tasks.
- OpenAI Gym
A toolkit for developing and comparing reinforcement learning algorithms.
- Proximal Policy Optimization (PPO)
A policy gradient method for reinforcement learning.
- Q-Learning
A value-based reinforcement learning algorithm.
Research Papers
- A Few Useful Things to Know About Machine Learning (2012)
A paper discussing important concepts in machine learning.
- Gradient Boosting Machine Learning (2001)
The original paper introducing Gradient Boosting.
- The Elements of Statistical Learning (2001)
A comprehensive book on statistical learning.
Model Evaluation and Tuning
- Bayesian Optimization
A method for optimizing hyperparameters using probabilistic models.
- Confusion Matrix
A tool for evaluating the performance of classification algorithms.
- Cross-Validation
A statistical method used to estimate the performance of a model.
- Grid Search
A method for hyperparameter optimization through exhaustive search.
- Precision, Recall, F1 Score
Metrics for evaluating the accuracy of a classification model.
Frameworks and Libraries
- CatBoost
A gradient boosting library with built-in support for categorical features.
- LightGBM
A fast, distributed, high-performance gradient boosting framework.
- PyTorch
An open-source machine learning framework popular for its dynamic computation graph.
- Scikit-learn
A comprehensive Python library for machine learning with efficient tools for data analysis.
- TensorFlow
An open-source platform for machine learning and deep learning by Google.
- XGBoost
A scalable, efficient, and widely-used gradient boosting library.
Feature Engineering
- Category Encoders
A collection of scikit-learn compatible transformers for encoding categorical features.
- FeatureTools
An open-source library for automated feature engineering.
- Missingno
A Python library for visualizing missing data.
- Pandas
A Python library for data manipulation and analysis.
- Principal Component Analysis (PCA)
A technique for dimensionality reduction.
Learning Resources
- Coursera: Machine Learning by Andrew Ng
A comprehensive course on machine learning.
- Fast.ai
Free courses and resources for practical machine learning.
- Google Machine Learning Crash Course
A fast-paced introduction to machine learning.
Datasets
- Data.gov
A portal for accessing public datasets.
- Google Dataset Search
A search engine for discovering datasets across the web.
- Kaggle Datasets
A platform for accessing diverse datasets and participating in competitions.
- OpenML
An open platform for sharing datasets and machine learning experiments.
- UCI Machine Learning Repository
A collection of datasets for machine learning research.
Unsupervised Learning
- DBSCAN (Density-Based Spatial Clustering)
A clustering algorithm that identifies dense regions of data points.
- Dimensionality Reduction
Techniques like PCA and t-SNE for reducing the number of features.
- Gaussian Mixture Models (GMM)
A probabilistic model for representing normally distributed subpopulations within an overall population.
- Hierarchical Clustering
A method of cluster analysis that builds a hierarchy of clusters.
- K-Means Clustering
A popular clustering algorithm for partitioning data into K clusters.
Showing a sample of 54 resources. View the full list on GitHub →