Abstract
In this paper, a novel Elman-type recurrent neural network (RNN) is presented for the binary classification of arbitrary symbol sequences, and a novel training method, including both evolutionary and local search methods, is evaluated using sequence databases from a wide range of scientific areas. An efficient, publicly available, software tool is implemented in C++, accelerating significantly (more than 40 times) the RNN weights estimation process using both simd and multi-thread technology. The experimental results, in all databases, with the hybrid training method show improvements in a range of 2% to 25% compared with the standard genetic algorithm.
Reference37 articles.
1. Recurrent neural network based language model;Mikolov;Proceedings of the INTERSPEECH-2010,2010
2. Towards classifying full-text using recurrent neural networks;Farkas;Proceedings of the 1995 Canadian Conference on Electrical and Computer Engineering,1995
3. Speech recognition with deep recurrent neural networks;Graves;Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing,2013
4. Document modeling with gated recurrent neural network for sentiment classification;Tang;Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing,2015
5. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks;Graves;Proceedings of the NIPS’08: 21st International Conference on Neural Information Processing Systems,2008