Skip to content

Recurrent Neural Network for modeling sequential data implemented using Python and Theano.

Notifications You must be signed in to change notification settings

mpezeshki/Recurrent-Neural-Networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Recurrent-Neural-Networks

Here's an RNN which is used for three kinds of output: real-valued, binary, and softmax. And for five kinds of activation function: sigmoid, tanh, relu, lstm, gru. To run the code you need to have Theano libary in your PYTHONPATH:

https://github.com/Theano/Theano

The results are then saved under *.png files: .png To test the model with different hyper-parameters, you need to modify any of testing function.

Running code with default parameters takes around 5 minutes on CPU.

Related resources

Graham Taylor's implementation:

https://github.com/gwtaylor/theano-rnn

Razvan Pascanu's implementation:

https://github.com/pascanur/trainingRNNs

Alex Grave's paper with a nice description of RNNs:

http://arxiv.org/pdf/1308.0850v5.pdf

Yoshua Bengio, Aaron Courville, and Ian Goodfellow book:

Deep Learning - Chapter 12

Notice

This code is distributed without any warranty, express or implied.

About

Recurrent Neural Network for modeling sequential data implemented using Python and Theano.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages