Skip to content

A multi-layer perceptron from scratch using Python and NumPy to classify the mnist dataset with a ~95% accuracy

Notifications You must be signed in to change notification settings

JoeyLee-22/MLP-From-Scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Multi Layer Perceptron

A multi layer perceptron from scratch using python and numpy to classify the mnist dataset with a ~95% accuracy

There are three different types of optimizers: vanilla, momentum, and adam

There are two different types of hidden layer activations: sigmoid and relu

There are two different types of outputer layer activations: sigmoid and softmax

About

A multi-layer perceptron from scratch using Python and NumPy to classify the mnist dataset with a ~95% accuracy

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages