Home

This is the documentation for cxxnet, a fast and short implementation for neural network in CPU/GPU ADD introduction

Getting started

• Read Tutorial to get started, play cxxnet on MNIST, run a feed forward neural network and convolution neural network in 3 minutes!

=

Parameter Setting

Global Setting

• Global Setting How to set global parameters for neural network

Data Input Setting

• Data Iterator How to set data iterator for your own experiment on MNIST, CIFAR, images and image binary.

Updater Setting

• Updater How to set hyper-parameters for learning procedure

Layer Setting

• Connection Layer How to set parameters for layer connect the neural network
• Activation Layer How to set activation layer in the neural network
• Convolution Layer How to set parameters for conv layer in the neural network
• Pooling Layer How to set parameters for pooling layer in the neural network
• Normalization Layer How to set parameters for normalization layer in the neural network

=

Code Layout

• core: core implementation of layers and updaters of neural net
• nnet: implementation of network that connects layers and updaters together
• io: handles data input and preprecessing
• utils: some utils to help simple tasks