Universal Approximation by Phase Series and Fixed-Weight Networks
- 1 May 1993
- journal article
- Published by MIT Press in Neural Computation
- Vol. 5 (3) , 359-362
- https://doi.org/10.1162/neco.1993.5.3.359
Abstract
In this note we show that weak (specified energy bound) universal approximation by neural networks is possible if variable synaptic weights are brought in as network inputs rather than being embedded in a network. We illustrate this idea with a Fourier series network that we transform into what we call a phase series network. The transformation only increases the number of neurons by a factor of two.Keywords
This publication has 1 reference indexed in Scilit:
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984