CURRENNT

CUDA-enabled machine learning library for recurrent neural networks

5.0 Stars (1)
128 Downloads (This Week)
Last Update:
Download currennt-0.2-rc1.zip
Browse All Files
Windows Linux

Screenshots

Description

CURRENNT is a machine learning library for Recurrent Neural Networks (RNNs) which uses NVIDIA graphics cards to accelerate the computations.

The library implements uni- and bidirectional Long Short-Term Memory (LSTM) architectures and supports deep networks as well as very large data sets that do not fit into main memory.

CURRENNT Web Site

Features

  • Uni- and bidirectional Long Short-Term Memory (LSTM) layers with forget gates and peepholes
  • Feedforward layers with tanh, logistic sigmoid and softmax activation functions
  • Deep neural network architectures supported
  • Cached on-line learning from large data sets (training data does not need to fit in main memory)
  • Reads training data from NetCDF files
  • Gradient descent with momentum
  • Supports on-line, batch and hybrid on-line/batch learning
  • Minimization of cross-entropy and squared error objectives
  • Supports regression and binary/multiclass classification tasks
  • Training with input activation noise for improved generalization
  • Autosave after each training epoch

KEEP ME UPDATED

User Ratings

★★★★★
★★★★
★★★
★★
1
0
0
0
0
ease 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 5 / 5
features 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 5 / 5
design 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 5 / 5
support 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 5 / 5
Write a Review

User Reviews

  • andysunhk
    1 of 5 2 of 5 3 of 5 4 of 5 5 of 5

    Good job. Thank you for your sharing.

    Posted 05/08/2015
Read more reviews

Additional Project Details

Intended Audience

Science/Research

User Interface

Command-line

Programming Language

C++

Registered

2013-07-08
Screenshots can attract more users to your project.
Features can attract more users to your project.