A comprehensive collection of Machine Learning and Deep Learning algorithms implemented from scratch in Python, with mathematical intution, detailed explanations, and practical examples.
Machine Learning Hub is an educational repository implementing machine learning algorithms from scratch instead of relying on high-level machine learning frameworks. The focus is to understand the mathematics, logic and optimization behind every algorithm.
To develop a strong foundation in machine learning with clean, well-structured, and reusable code.
- 📚 Machine Learning algorithms implemented from scratch
- 🧠 Mathematical intuition and derivations
- 💻 Clean, readable, and well-documented Python code
- 📊 Practical examples with datasets
- 📈 Data visualization for better understanding
- 🚀 Step-by-step learning progression
- 🔄 Continuous repository updates
Machine-Learning-Hub/
│
├── 01_Linear_Regression/
├── 02_Logistic_Regression/
├── 03_KNN/
├── 04_Naive_Bayes/
├── 05_Decision_Tree/
├── 06_Random_Forest/
├── 07_Support_Vector_Machine/
├── 08_KMeans/
├── 09_Principal_Component_Analysis/
├── 10_Neural_Network/
├── 11_Backpropagation/
├── 12_Gradient_Descent/
├── 13_CNN/
├── 14_RNN/
├── 15_LSTM/
├── 16_Transformer/
│
├── datasets/
├── assets/
├── README.md
└── LICENSE
- ✅ Linear Regression
- ⏳ Logistic Regression
- ⏳ K-Nearest Neighbors (KNN)
- ⏳ Naive Bayes
- ⏳ Decision Tree
- ⏳ Random Forest
- ⏳ Support Vector Machine (SVM)
- ⏳ K-Means Clustering
- ⏳ Principal Component Analysis (PCA)
- ⏳ Neural Networks
- ⏳ Gradient Descent
- ⏳ Backpropagation
- ⏳ Convolutional Neural Networks (CNN)
- ⏳ Recurrent Neural Networks (RNN)
- ⏳ Long Short-Term Memory (LSTM)
- ⏳ Transformer Architecture
- Python
- NumPy
- Pandas
- Matplotlib
- Build every algorithm from scratch.
- Understand the mathematical foundations of Machine Learning.
- Improve problem-solving and implementation skills.
- Create reusable educational implementations.
- Build a strong foundation for Deep Learning and Artificial Intelligence.
- Implement optimization algorithms
- Build a custom neural network library
- Implement automatic differentiation (Autograd)
- Build transformer models from scratch
- Train small language models
- Develop an educational Machine Learning framework
Contributions, suggestions, and improvements are welcome.
If you find an issue or have ideas for enhancement, feel free to open an issue or submit a pull request.
This project is licensed under the Apache License 2.0.
See the LICENSE file for more information.
Your support helps motivate continued development and encourages others to discover the project. If you find this repository helpful, consider giving it a star 🌟.
Learn • Implement • Experiment • Understand