A Fast Algorithm for Recurrent Neural Networks

WANG Ju; LIU Heping

doi:10.13374/j.issn1001-053x.2000.01.047

Volume 22 Issue 1

Aug. 2021

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Engineering > 2000 > 22(1): 89-92

WANG Ju, LIU Heping. A Fast Algorithm for Recurrent Neural Networks[J]. Chinese Journal of Engineering, 2000, 22(1): 89-92. doi: 10.13374/j.issn1001-053x.2000.01.047

Citation:

WANG Ju, LIU Heping. A Fast Algorithm for Recurrent Neural Networks[J]. Chinese Journal of Engineering, 2000, 22(1): 89-92. doi: 10.13374/j.issn1001-053x.2000.01.047

WANG Ju, LIU Heping. A Fast Algorithm for Recurrent Neural Networks[J]. Chinese Journal of Engineering, 2000, 22(1): 89-92. doi: 10.13374/j.issn1001-053x.2000.01.047

Citation:

WANG Ju, LIU Heping. A Fast Algorithm for Recurrent Neural Networks[J]. Chinese Journal of Engineering, 2000, 22(1): 89-92. doi: 10.13374/j.issn1001-053x.2000.01.047

PDF( 477 KB)

A Fast Algorithm for Recurrent Neural Networks

doi: 10.13374/j.issn1001-053x.2000.01.047

WANG Ju,
LIU Heping

Information Engineering School, UST Beijing, Beijing 100083, China

Received Date: 1999-07-19

Abstract

Abstract

A new fast learning algorithm for recurrent neural networks is proposed. By introducing the signal flow graphs technique, it overcomes the disadvantage of complexity of the gradient of the error function. And for more fast convergence, the BFGS method is used. Simulation results show that the proposed algorithm converges faster than the traditional algorithm.
- recurrent neural networks,
- dynamic BP algorithm,
- signal flow graphs,
- BFGS