Knowledge-based design of ANNs

Eyal Kolman*, Michael Margaliot

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

Corollaries 3.1-3.10 in Chapter 3 provide a transformation between a FARB and an ANN. The ANN type (i.e., feedforward, first-order RNN, or second-order RNN), structure, and parameter values, are determined directly from the FARB structure and parameters. This suggests a novel scheme for knowledge-based design (KBD) of ANNs. Given the initial knowledge, determine the relevant inputs, denoted x1,...,xm] and the number of outputs. For each output, restate the initial knowledge in the form of an FRB relating some subset of the inputs {y1,...,yk} ⊆ {x1,..., xm} to this output. In this FRB, each yi must be characterized using two fuzzy terms. The Then-part of each rule must be decomposed as a sum ao ± a1 ±...± ak, where the signs are determined according to the If-part of the rule. More rules are added to the FRB, if necessary, until it contains 2k fuzzy rules, expanding all the possible permutations of the input variables. The output of each added rule is again a linear sum of the ai s with appropriate signs. MFs for each input variable are chosen such that (2.3) holds.

Original languageEnglish
Title of host publicationKnowledge-Based Neurocomputing
Subtitle of host publicationA Fuzzy Logic Approach
EditorsEyal Kolman, Michael Margaliot
PublisherSpringer Berlin Heidelberg
Pages59-76
Number of pages18
ISBN (Print)9783540880769
DOIs
StatePublished - 2009

Publication series

NameStudies in Fuzziness and Soft Computing
Volume234
ISSN (Print)1434-9922

Fingerprint

Dive into the research topics of 'Knowledge-based design of ANNs'. Together they form a unique fingerprint.

Cite this