Skip to content

ttomf/neural-network

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 

Repository files navigation

Neural Network

A minimal feedforward neural network from scratch using NumPy.

Features

  • Activations: sigmoid, tanh, ReLU, softmax, identity
  • Training: mini-batch SGD with backpropagation
  • Classification & regression support
  • Save/load via pickle

Usage

from nn import Net, Activation

net = Net()
net.build(layers=[784, 128, 64, 10],
          activations=[Activation.relu, Activation.relu, Activation.softmax])

net.train(data, labels, rate=0.01, epochs=50, batch_size=32, classification=True)

net.save("model.pkl")
net.load("model.pkl")

About

A minimal feedforward neural network

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages