Improvement of bidirectional recurrent neural network for learning long-term dependencies

Proceedings - International Conference on Pattern Recognition

Volumn 4, Issue , 2004, Pages 593-596

  Chen, Jinmiao ^a   Chaudhari, Narendra S ^a  

^a NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

Author keywords

[No Author keywords available]

Indexed keywords

BIDIRECTIONAL RECURRENT NEURAL NETWORKS (BRNN); PROTEIN SECONDARY STRUCTURE (PSS); RECURRENT NEURAL NETWORKS (RNN); VANISHING GRADIENTS;

DATA STORAGE EQUIPMENT; DNA; ERROR ANALYSIS; FUNCTIONS; INFORMATION ANALYSIS; LEARNING ALGORITHMS; MATHEMATICAL MODELS; PROBLEM SOLVING; PROTEINS; VECTORS;

NEURAL NETWORKS;

EID: 10044265071     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICPR.2004.1333842     Document Type: Conference Paper

References (3)

1. Y. Bengio, P. Simard, and P. Frasconi. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2): 157-166, 1994.
2. J. F. Kolen and S. C. Kremer, editors. A Field Guide to Dynamical Recurrent Networks. John Wiley & Sons, January 2001.
3. G. Pollastri, D. Przybylski, and P. B. B. Rost. Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles. Proteins, 47:228-235, 2002.