Skip to content

jorelhaggard/Backpropagation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Backpropagation

A backpropagation algorithm for binary classification written using Numpy.

This algorithm is applicable to data sets of size (m, n), but will not generalize to networks with hidden layers.

When called, this function will iterate over each training example in m, then return the computed values of dJ/dw and dJ/db.

dJ/dw is an array of size (n, 1) containing the values of the gradient of the cost, J, with respect to each w[j].

dJ/db is a scalar with value equivalent to the gradient of the cost, J, with respect to the bias, b.

About

A backpropagation algorithm written using Numpy.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages