CURRENNT swMATH ID: 12814 Software Authors: Weninger, Felix Description: Introducing CURRENNT: the Munich open-source CUDA recurrent neural network toolkit. 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 url{http://sourceforge.net/p/currennt}. Homepage: http://sourceforge.net/projects/currennt/ Keywords: parallel computing; deep neural networks; recurrent neural networks; long short-term memory Related Software: PyBrain; RNNLIB; CUDA Cited in: 1 Document Standard Articles 1 Publication describing the Software, including 1 Publication in zbMATH Year Introducing CURRENNT: the Munich open-source CUDA recurrent neural network toolkit. Zbl 1358.68243Weninger, Felix 2015 Cited by 1 Author 1 Weninger, Felix Cited in 1 Serial 1 Journal of Machine Learning Research (JMLR) Cited in 1 Field 1 Computer science (68-XX) Citations by Year