Skip to content

Built a custom neural network from scratch simply with mathematics and python's Numpy package. Network's accuracy: 93.5%.

Notifications You must be signed in to change notification settings

ifunanyaScript/Artificial-Neural-Network-from-scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 

Repository files navigation

Custom Artificial Neural Network.

This is an implementation of an Artificial Neural Network using just mathematics and Python's numpy package, without fancy deep learning frameworks.
This network was trained on the famous MNIST dataset. The network achieved 93.5% accuracy on the test dataset.

All the functions used to build the ANN is available here If you're reading this, I hope you look at the notebook. I tried to simplify the mathematics behind neural networks and it's entirely easy to understand.

Drop a ⭐, Thanks!

About

Built a custom neural network from scratch simply with mathematics and python's Numpy package. Network's accuracy: 93.5%.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published