https://github.com/titu1994/keras-minimal-rnn

Keras implementation of MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks
https://github.com/titu1994/keras-minimal-rnn

keras minimal minimalrnn rnn

Last synced: 3 months ago
JSON representation

Keras implementation of MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks

• Host: GitHub
• URL: https://github.com/titu1994/keras-minimal-rnn
• Owner: titu1994
• License: mit
• Created: 2017-11-23T17:11:45.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-03-22T02:41:17.000Z (over 7 years ago)
• Last Synced: 2025-03-25T05:34:08.376Z (3 months ago)
• Topics: keras, minimal, minimalrnn, rnn
• Language: Python
• Homepage:
• Size: 9.04 MB
• Stars: 17
• Watchers: 4
• Forks: 6
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Keras MinimalRNN

Keras implementation of [MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks](https://arxiv.org/abs/1711.06788).

## Network graph of MinimalRNNs (from the paper):







# Usage

Import `minimal_rnn.py` and use either the `MinimalRNNCell` or `MinimalRNN` layer

```python

from minimal_rnn import MinimalRNN 

# this imports the layer rather than the cell

ip = Input(...)  # Rank 3 input shape

x = MinimalRNN(units=128)(ip)

...

```