Generalized Regularization Networks with a Particular Class of Bell-Shaped Basis Function

Akira NAGAMI  Hirofumi INADA  Takaya MIYANO  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E81-A   No.11   pp.2443-2448
Publication Date: 1998/11/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks
radial basis function network,  neural network,  neuro device,  chaos,  time series prediction,  

Full Text: PDF(554.1KB)>>
Buy this Article

A generalized radial basis function network consisting of (1 + cosh x)-1 as the basis function of the same class as Gaussian functions is investigated in terms of the feasibility of analog-hardware implementation. A simple way of hardware-implementing (1 + cosh x)-1 is proposed to generate the exact input-output response curve on an analog circuit constructed with bipolar transistors. To demonstrate that networks consisting of the basis function proposed actually work, the networks are applied to numerical experiments of forecasting chaotic time series contaminated with observational random noise. Stochastic gradient descent is used as learning rule. The networks are capable of learning and making short-term forecasts about the dynamic behavior of the time series with comparable performance to Gaussian radial basis function networks.