Search for:

We aggregate information from all open source repositories to provide the most of useful open source products, from Enterprise product to small libraries across all platforms. Please search and find what you want.

CURRENNT

Posted on by Robin Ding Leave a comment Machine Learning
5.0

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.

You’re probably paying too much for cell phone service. Wirefly compares hundreds of plans to help you save. Enter what you need (minutes, data, texts) into Wirefly’s innovative plan comparison tools and see your savings instantly.

Post Views: 235

Related Projects:

  1. Kaldi
  2. Scene
  3. English-Khmer S. Machine Translation
  4. Ceka
Website https://currennt.sourceforge.io/
Tags
License GNU General Public License version 3.0 (GPLv3)
Platform Linux Windows
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