Relating the slope of the activation function and the learning rate within a recurrent neural network

Neural Computation

Volumn 11, Issue 5, 1999, Pages 1069-1077

  Mandic, Danilo P ^a   Chambers, Jonathon A ^a  

^a IMPERIAL COLLEGE LONDON   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0000005113     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976699300016340     Document Type: Article

References (8)

1. Haykin, S. (1994). Neural networks - A comprehensive foundation. Englewood Cliffs, NJ: Prentice Hall.
2. Narendra, K. S., & Parthasarathy, K. (1990). Identification and control of dynamical systems using neural networks. IEEE Transaction on Neural Networks, 1(1), 4-27.
3. Pineda, F. (1987). Generalization of backpropagation to recurrent neural networks. Physical Review Letters, 59, 2229-2232.
4. Robinson, A. J., & Fallside, F. (1987). The utility driven dynamic error propagation network (Tech. Rep. CUED/F-INFENG/TR.1). Cambridge: Cambridge University Engineering Department.
5. Thimm, G., Moerland, P., & Fiesler, E. (1996). The interchangeability of learning rate and gain in backpropagation neural networks. Neural Computation, 8, 451-460.
6. Werbos, P. (1990). Backpropagation through time: What it does and how to do it. Proceedings of the IEEE, 78(10), 1550-1560.
7. Williams, R., & Zipser, D. (1989). A learning algorithm for continually running fully recurrent neural networks. Neural Computation, 1, 270-280.
8. Zurada, J. (1992). Introduction to artificial neural systems. St. Paul, MN: West Publishing Company.