Skip to content

Latest commit

 

History

10 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

Neural Network From Scratch

This is an implementation of a simple multilayer neural network with one input, hidden, and output layer without the use of any existing deep learning libraries (e.g. TensorFlow, PyTorch). The network uses a sigmoid activation function and the weights are updated using gradient descent and momentum. The network is trained and tested on the MNIST handwritten digit dataset.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages