Small Depth Polynomial Size Neural Networks
- 1 December 1990
- journal article
- Published by MIT Press in Neural Computation
- Vol. 2 (4) , 402-404
- https://doi.org/10.1162/neco.1990.2.4.402
Abstract
For polynomially bounded weights and polylogarithmic precision, analog neural networks of polynomial size and depth 3 are strictly more powerful than those of polynomial size and depth 2.Keywords
This publication has 1 reference indexed in Scilit:
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989