Bull. Coll. Med. Sci. Tohoku Univ. 11(1): 1〜6，2002

A General Second-order Neural Unit

Noriyasu HOMMA1,2 and Madan M. GUPTA2

1Department of Radiological Technology, College of
Medical Sciences, Tohoku University
2Intelligent Systems Research Laboratory, College of
Engineering, University of Saskatchewan


一般化2次ニューラルユニット

本間経康1,2, Madan M. Gupta2

1東北大学医療技術短期大学部 診療放射線技術学科
2サスカッチワン大学工学部 知的システム研究所

Key words: Neural Networks, Second-order Systems, Learning Algorithms, Classification, Function Approximation


　　A general second-order neural unit (SONU) is developed using a new matrix form for providing a general second-order combination of the input signals and the synaptic weights. It is shown that the widely used linear combination neural units are only a subset of the proposed SONUs. Simulation studies demonstrate that the learning and generalization abilities of the proposed SONUs are much superior to that of the linear combination neural units.