A study on generalization ability of 3-layer recurrent neural networks

Author

Ninomiya, Hiroshi ; SASAKI, Ayako

Author_Institution

Dept. of Inf. Sci., Shonan Inst. of Technol., Fujisawa, Japan

Volume

2

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

1063

Lastpage

1068

Abstract

In this paper, we report a study on the generalization ability of 3-layer recurrent neural networks (3LRNN). 3LRNN are composed of the both of the feed-forward and feedback connections. The generalization ability of 3LRNN is compared with one of 3-layer feed-forward neural networks through the computer simulations. It is shown that 3LRNN are not only almost equivalent to 3LFNN but also much superior to one on a certain condition from the viewpoint of the generalization capability. Furthermore, we investigate the generalization ability of 3LRNN with the neurons that have the step functions as the input-output property

Keywords

digital simulation; feedback; learning (artificial intelligence); recurrent neural nets; 3-layer recurrent neural networks; computer simulations; feed-forward neural networks; generalization ability; Artificial neural networks; Computer simulation; Feedforward neural networks; Feedforward systems; Iterative algorithms; Multi-layer neural network; Neural networks; Neurofeedback; Neurons; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007641

Filename

1007641