Skip to content

Bonifatius94/BackpropNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

BackpropNet

About

BackpropNet provides basic neural network capabilities for .NET to train feed-forward models. It is meant to fuel lightweight decision making tasks through reinforcement learning.

Supported Features

Layers

  • Dense
  • ReLU
  • Softmax

Losses

  • Mean Squared Error
  • Crossentropy (Full / Sparse)

Optimizers

  • Gradient Descent (Vanilla)
  • Adam

Examples

  • Regression: sin(x)
  • Classification: MNIST

License

BackpropNet is available under the terms of the GPLv3 license.

About

basic neural network capabilities for .NET

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages