Skip to content

A Jupyter notebook building and training a Neural Network from scratch with NumPy

License

Notifications You must be signed in to change notification settings

hodgesmr/neural_network_from_scratch

Repository files navigation

Neural Network From Scratch in Python

This is a Jupyter Notebook that walks through creating a Neural Network from scratch, only using NumPy. It covers many of the basic concepts such as Neural Network structure, forward propagation, back propagation, activation functions, and learning rates. It builds a model that classifies the MNIST handwritten digit data set with ~90% accuracy.

License

All code is provided under the BSD 3-Clause license.

A Matt Hodges project

This project is maintained by @hodgesmr.

Please use it for good, not evil.

About

A Jupyter notebook building and training a Neural Network from scratch with NumPy

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published