Skip to content

kinghchan/custom_neural_network

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 

Repository files navigation

custom_neural_network

A neural network written with NumPy

Two distinctive features of this particular code is that

  1. you can vary the number of layers and output neurons and
  2. the training samples are completely vectorised.

This notebook will go through how the n-layer, m-output (n and m are varying integers) neural network works. This is a fully vectorised network, meaning that the use of for-loops is replaced with numpy vectors whenever possible to reduce the run-time.

About

A neural network written with NumPy

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published