Title :
Capabilities of three-layered perceptrons
Author :
Irie, Bunpei ; Miyake, Sei
Author_Institution :
Auditory & Visual Perception Res. Lab., ATR, Osaka, Japan
Abstract :
A theorem is proved to the effect that three-layered perceptrons with an infinite number of computing units can represent arbitrary mapping if the desired mapping and the input-output characteristics of the computing units satisfy some constraints. The proof is constructive, and each coefficient is explicitly presented. The theorem theoretically guarantees a kind of universality for three-layered perceptrons. Although two-layered perceptrons (simple perceptrons) cannot represent arbitrary functions, three-layers prove necessary and sufficient. The relationship between the model used in the proof and the distributed storage and processing of information is also discussed.<>
Keywords :
neural nets; distributed processing; distributed storage; neural nets; three-layered perceptrons; two-layered perceptrons; universality; Neural networks;
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/ICNN.1988.23901