Back to Search
Start Over
Introducing CURRENNT: The Munich Open-Source CUDA RecurREnt Neural Network Toolkit.
- Source :
-
Journal of Machine Learning Research . 2015, Vol. 16, p547-551. 5p. - Publication Year :
- 2015
-
Abstract
- In this article, we introduce CURRENNT, an open-source parallel implementation of deep recurrent neural networks (RNNs) supporting graphics processing units (GPUs) through NVIDIA's Computed Unified Device Architecture (CUDA). CURRENNT supports uni- and bidirectional RNNs with Long Short-Term Memory (LSTM) memory cells which overcome the vanishing gradient problem. To our knowledge, CURRENNT is the first publicly available parallel implementation of deep LSTM-RNNs. Benchmarks are given on a noisy speech recognition task from the 2013 2nd CHiME Speech Separation and Recognition Challenge, where LSTM-RNNs have been shown to deliver best performance. In the result, double digit speedups in bidirectional LSTM training are achieved with respect to a reference single-threaded CPU implementation. CURRENNT is available under the GNU General Public License from http://sourceforge.net/p/currennt. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 15324435
- Volume :
- 16
- Database :
- Academic Search Index
- Journal :
- Journal of Machine Learning Research
- Publication Type :
- Academic Journal
- Accession number :
- 103335554