Blocks 0.1

bart van merrienboer, dzmitry bahdanau, — Mon, 30 Mar 2015 22:25:02 -0000

Blocks is a framework that helps you build neural network models on top of Theano. Currently it supports and provides:

Constructing parametrized Theano operations, called "bricks", with a large number of neural network layers built-in
Pattern matching to select variables and bricks in large models
Algorithms to optimize your model such as SGD, Adadelta, Adam
Saving and resuming of training
Monitoring and analyzing values during training progress (on the training set as well as on test sets)
Application of graph transformations, such as dropout

mloss.org Blocks