Giter VIP home page Giter VIP logo

rnn-em's Introduction

RNN-EM

Recurrent Neural Network with External Memory in Keras

This is an implementation of a special kind of RNN which uses a 3-D external memory component to learn long range patterns in sequences. This is in contrast to LSTMs and GRUs which use 2-D hidden states. Though slower than LSTMs and GRUs, RNN-EMs can yield better results with lesser number of parameters.

API

RNN-EM implements the Recurrent api in Keras. RNN-EM requires 2 additional arguments:

  • nb_slots: int. Number of memory slots.
  • memory_size: int. Size of each memory slot.

Example

from keras.models import Sequential

model = Sequential()
model.add(RNNEM(input_dim=10, output_dim=10, nb_slots=5, memory_size=10))
model.compile(loss='mse', optimizer='sgd')

rnn-em's People

Contributors

farizrahman4u avatar

Watchers

James Cloos avatar Shubham Pachori avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.