Skip to content

A minimalistic implementation of a neural network and backpropagation using only NumPy

License

Notifications You must be signed in to change notification settings

zanarashidi/neural-network-from-scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Simple Feed Forward Neural Network and Backpropagation using NumPy

About

This repository contains a simple and customizable feed forward neural network and backpropagation using only NumPy. The dataset used for this experiment is MNIST.

How to use

$ python feedforward.py

Hyperparameters

Hyperparameters such as the number of hidden layers, number of neurons, activation functions, learning rate, etc can be modified inside the code.

Requirements

The main requirements for this project are Python and NumPy.

About

A minimalistic implementation of a neural network and backpropagation using only NumPy

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages