A cascaded artificial neural network architecture with novel robustness

Author

Kamruzzaman, Joarder ; Kumagai, Yukio ; Hikita, Hiromitsu

Author_Institution

Muroran Inst. of Technol., Hokkaido, Japan

fYear

1992

fDate

16-20 Nov 1992

Firstpage

1235

Abstract

Two 2-layer networks are first trained independently by delta rule and then cascaded. The middle layer can be viewed as a hidden layer and is trained to attain preassigned saturated outputs in response to the training set. Simulation results reveal that generalization ability of this cascaded network is far better than that of conventional back-propagation networks. Suggestions about the hidden coding in the cascaded network are presented. This network also learns considerably faster than BP networks. In large scale integrated neural network systems this network would enhance the overall performance

Keywords

cascade networks; encoding; feedforward neural nets; generalisation (artificial intelligence); learning (artificial intelligence); cascaded artificial neural network architecture; delta rule; generalization ability; hidden coding; hidden layer; large scale integrated neural network systems; performance; robustness; Artificial neural networks; Backpropagation algorithms; Character recognition; Image coding; Image processing; Large scale integration; Multi-layer neural network; Neural networks; Nonhomogeneous media; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Singapore ICCS/ISITA '92. 'Communications on the Move'

Print_ISBN

0-7803-0803-4

Type

conf

DOI

10.1109/ICCS.1992.255062

Filename

255062