Please use this identifier to cite or link to this item:
Title: Controlled learning environment of enhanced perception.
Authors: Teh, Hoon Heng 
Yu, Wellington C.P.
Issue Date: 1988
Citation: Teh, Hoon Heng,Yu, Wellington C.P. (1988). Controlled learning environment of enhanced perception. : 452-460. ScholarBank@NUS Repository.
Abstract: Some basic features of multi-layer perceptrons are sketched. Some of the shortcomings of these perceptrons are pointed out, and ways of retaining their strengths but overcoming their shortcomings are proposed. A class of networks called inference networks is introduced in order to demonstrate that logical reasoning capability can also be modeled using networks. The class of multi layer perceptrons and inference networks is then unified into a single class of networks, called enhanced perceptrons. One important theorem obtained is that for any given pair of pattern-sets, there always exists an enhanced perceptron with only one hidden layer to match the given patterns. The patterns can be image patterns, attribute patterns, or logical patterns. The proof of this theorem is by constructive algorithm. Once a solution is obtained, other solutions with a controlled degree of error tolerance can then be generated through some learning algorithms.
ISBN: 0818608978
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

checked on Sep 26, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.