Improving the Learning Speed in 2-Layered LSTM Network by Estimating the Configuration of Hidden Units and Optimizing Weights Initialization
- 5 September 2008
- book chapter
- Published by Springer Nature
- p. 109-118
Abstract
No abstract availableKeywords
This publication has 9 references indexed in Scilit:
- Training Recurrent Networks by EvolinoNeural Computation, 2007
- Recurrent Neural Networks for Music ComputationINFORMS Journal on Computing, 2006
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent netsNeural Networks, 2003
- Principles of Computerized Tomographic Imaging2001
- Long Short-Term MemoryNeural Computation, 1997
- Gradient calculations for dynamic recurrent neural networks: a surveyIEEE Transactions on Neural Networks, 1995
- Generalization of backpropagation with application to a recurrent gas market modelNeural Networks, 1988
- Capabilities of three-layered perceptrons1988