Title :
Construction of multiplier by neural network
Author :
Toda, Naohiro ; Usui, Shiro
Author_Institution :
Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan
Abstract :
Construction of a neural network using a neural multiplier module (NMM) is proposed. The learning results show that a fairly simple structure can be used. The proposed method can be used effectively to set the initial state (structure and weighting parameter of network) for learning. Furthermore, this method can be applied to prewiring. There is no evidence that the structure is optimum
Keywords :
multiplying circuits; neural nets; network structure; network weighting parameter; neural multiplier module; neural network; prewiring; Computer networks; Design methodology; Feedforward neural networks; Learning systems; Multi-layer neural network; Neural networks; Nonlinear systems; Polynomials; Taylor series;
Conference_Titel :
Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century., Proceedings of the Annual International Conference of the IEEE Engineering in
Conference_Location :
Seattle, WA
DOI :
10.1109/IEMBS.1989.96592
