Emergence of learning: an approach to coping with NP-complete problems in learning

Author

Lu, Bao-Liang ; Ichikawa, Michinori

Author_Institution

Lab. for Brain-Operative Device, RIKEN, Wako, Japan

Volume

4

fYear

2000

fDate

2000

Firstpage

159

Abstract

Various theoretical results show that learning in conventional feedforward neural networks such as multilayer perceptrons is NP-complete. In this paper we show that learning in min-max modular (M ³) neural networks is tractable. The key to coping with NP-complete problems in M³ networks is to decompose a large-scale problem into a number of manageable, independent subproblems and to make the learning of a large-scale problem emerge from the learning of a number of related small subproblems

Keywords

character recognition; computational complexity; feedforward neural nets; learning (artificial intelligence); minimisation; multilayer perceptrons; NP-complete problems; character recognition; computational complexity; feedforward neural networks; large-scale problem; min-max modular; minimisation; multilayer perceptrons; supervised learning; Biological neural networks; Computational complexity; Feedforward neural networks; Large-scale systems; Management training; Multi-layer neural network; NP-complete problem; Neural networks; Supervised learning; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.860766

Filename

860766