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
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.