Multilayer feedforward networks are universal approximators
Neural Networks
Fault diagnosis in railway track circuits using Dempster-Shafer classifier fusion
Engineering Applications of Artificial Intelligence
| Hi-index | 0.00 |
This article addresses the issue of symbolic processing with Multi-LayerPerceptrons through encoding. Given an encoding, we propose a lower boundof the number of parameters for an MLP to perform a random mapping of itsinput symbolic space to its output symbolic space. In the case of what wecall binary encoding, the needed number of parameters may betheoretically computed. Given these two results, we show that the mostefficient encodings are the ones which use one input unit per value.