Transparent NumPy implementations of machine-learning algorithms with runnable examples for studying their inner workings.
Project overview
It presents algorithm implementations and example scripts with an emphasis on accessibility over computational optimization.
Project type
Model Development · Data Processing · Learning Resources
Use cases
Learning & Education
Deployment
Refer to project documentation
License
MIT
Best for
Learners and developers inspecting how machine-learning algorithms are implemented.
Key capabilities
Provides from-scratch implementations of models like Adaboost, Decision Tree, Gradient Boosting, etc.
Provides from-scratch implementations of algorithms including Apriori, Autoencoder, DBSCAN, FP-Growth, etc.
Ships runnable Python scripts demonstrating various algorithms, such as polynomial regression, CNN classification, and genetic algorithms.
Limitations and risks
Not optimized for computationally efficient operations
Getting started
git clone https://github.com/eriklindernoren/ML-From-Scratch; cd ML-From-Scratch; python setup.py install; python mlfromscratch/examples/polynomial_regression.py
Evidence and sources
GitHub project description: 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 regre…
README: Python implementations of some of the fundamental Machine Learning models and algorithms from scratch. The purpose of this project is not to produce as optimized and computational…
README: Figure: Classification of the digit dataset using CNN.