Multilayer feedforward potential function network
- 1 January 1988
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 161-171 vol.1
- https://doi.org/10.1109/icnn.1988.23844
Abstract
The authors present a multilayer feedforward network, called the Gaussian potential function network (GPFN), performing association or classification based on a set of potentially fields synthesized over the domain of input space by a number of Gaussian potential function units (GPFUs). A GPFU as a basic component of the GPFN is designed to generate a Gaussian form of a potential field. A weighted summation of Gaussian potential fields generated by a suitable number of GPFUs provides an arbitrary shape of a potential field over the domain of input space. The authors also present a detailed learning algorithm for the GPFN. Learning consists of the determination of the minimally necessary number of GPFUs and the adjustment of the locations and shapes of the individual Gaussian potential fields defined by GPFUs as well as the summation weights. The learning of the minimally necessary number of GPFUs is based on the control of the effective radius of GPFUs, while the parameter learning is based on the gradient descent procedure.Keywords
This publication has 6 references indexed in Scilit:
- Adaptive bidirectional associative memoriesApplied Optics, 1987
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- Mechanisms of planning and problem solving in the brainMathematical Biosciences, 1979