machine learning algorithms implementation
Minimal and clean Python implementations of common machine learning algorithms, written with numpy/scipy/autograd for educational purposes.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose when you prefer Jupyter notebooks with visualizations and first-principles derivations over standalone scripts.
ML algorithms implemented and derived from first-principles in Jupyter Notebooks and NumPy
choose when you want interactive Jupyter demos with math explanations and visualizations.
🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained
choose when you want a broad collection of tutorial-style examples from an instructor's courses.
A collection of machine learning examples and tutorials.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
choose when you want plain Python implementations without notebooks, but note it is not actively maintained.
Plain python implementations of basic machine learning algorithms
These projects were analysed and named MLAlgorithms among their alternatives. The relationship is not symmetric — how MLAlgorithms rates them is a separate judgement, made when MLAlgorithms is analysed in its own right.
calls MLAlgorithms “Choose for minimal, clean NumPy implementations that are actively maintained.”
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
calls MLAlgorithms “Choose for minimal, dependency-free Python implementations with a cleaner codebase than the seed.”
🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained
calls MLAlgorithms “choose for a compact, clean and current implementation reference of ML algorithms.”
100-Days-Of-ML-Code中文版
calls MLAlgorithms “For clean, framework-free implementations of classic ML algorithms.”
A resource for learning about Machine learning & Deep Learning
calls MLAlgorithms “choose to study minimal, clean implementations of algorithms instead of a guided daily challenge.”
100 Days of ML Coding
calls MLAlgorithms “Choose for a framework-free, minimal Python implementation of classic ML algorithms instead of TensorFlow-based examples.”
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
calls MLAlgorithms “Choose when you want minimal standalone implementations of ML algorithms for reference, not a full tutorial.”
⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.
calls MLAlgorithms “Choose for terse algorithm implementations without the book's narrative.”
The "Python Machine Learning (1st edition)" book code repository and info resource
calls MLAlgorithms “Use this if you want minimal implementations as plain Python code with no PRML textbook narrative”
PRML algorithms implemented in Python
calls MLAlgorithms “When you want clean, minimal implementations of common ML algorithms without the extra tutorial fluff.”
A collection of machine learning examples and tutorials.
calls MLAlgorithms “Pick for compact pure-Python implementations of core ML algorithms to see how they work internally.”
Notebooks and code for the book "Introduction to Machine Learning with Python"
calls MLAlgorithms “choose only for minimal, clean ML implementations; seed is a full teaching guide”
Python Data Science Handbook: full text in Jupyter Notebooks
calls MLAlgorithms “Minimal ML algorithm implementations, a narrow subset without DL/NLP.”
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。
calls MLAlgorithms “when you need clean minimal algorithm implementations as a code reference, not a full learning path.”
Open Machine Learning Course
calls MLAlgorithms “Choose for quick, minimal algorithm implementation snippets, not for gaining a structured ML education.”
:speech_balloon: Machine Learning Course with Python:
calls MLAlgorithms “When you want minimal, clean Python implementations of core ML algorithms for reading, not a PyTorch notebook course.”
AI实战-practicalAI 中文版