Sciweavers

Share
ICPR
2004
IEEE

Improvement of Bidirectional Recurrent Neural Network for Learning Long-Term Dependencies

9 years 6 months ago
Improvement of Bidirectional Recurrent Neural Network for Learning Long-Term Dependencies
Bidirectional recurrent neural network(BRNN) is a noncausal generalization of recurrent neural network(RNN). It can not learn remote information efficiently due to the problem of vanishing gradients. To limit this problem, we propose segmented-memory recurrent neural network(SMRNN) and replace the standard RNNs in BRNN with SMRNNs. The resulting architecture is called bidirectional segmented-memory recurrent neural network(BSMRNN). We test the BSMRNN on the problem of information latching and provide results showing that BSMRNN performs better on long-term dependency problem than BRNN.
Jinmiao Chen, Narendra S. Chaudhari
Added 09 Nov 2009
Updated 09 Nov 2009
Type Conference
Year 2004
Where ICPR
Authors Jinmiao Chen, Narendra S. Chaudhari
Comments (0)
books