dc.contributor.author Lappas, G. dc.contributor.author Frank, R. dc.contributor.author Albrecht, A. dc.date.accessioned 2010-02-18T11:35:14Z dc.date.available 2010-02-18T11:35:14Z dc.date.issued 2006 dc.identifier.citation Lappas , G , Frank , R & Albrecht , A 2006 , ' A Computational Study on Circuit Size vs. Circuit Depth ' , International Journal on Artificial Intelligence Tools , vol. 15 , no. 2 , pp. 143-161 . https://doi.org/10.1142/S0218213006002606 dc.identifier.issn 0218-2130 dc.identifier.other PURE: 97430 dc.identifier.other PURE UUID: 2a8b0381-b40c-4e7b-b63b-b959b8abfb29 dc.identifier.other dspace: 2299/4291 dc.identifier.other Scopus: 33746225528 dc.identifier.uri http://hdl.handle.net/2299/4291 dc.description Original article can be found at: http://www.worldscinet.com/ijait/mkt/archive.shtml Copyright World Scientific Publishing Company DOI: 10.1142/S0218213006002606 [Full text of this article is not available in the UHRA] dc.description.abstract We investigate the circuit complexity of classification problems in a machine learning setting, i.e. we attempt to find some rule that allows us to calculate a priori the number of threshold gates that is sufficient to achieve a small error rate after training a circuit on sample data ${\mathcal S}_L$. The particular threshold gates are computed by a combination of the classical perceptron algorithm with a specific type of stochastic local search. The circuit complexity is analysed for depth-two and depth-four threshold circuits, where we introduce a novel approach to compute depth-four circuits. For the problems from the UCI Machine Learning Repository we selected and investigated, we obtain approximately the same size of depth-two and depth-four circuits for the best classification rates on test samples, where the rates differ only marginally for the two types of circuits. Based on classical results from threshold circuit theory and our experimental observations on problems that are not linearly separable, we suggest an upper bound of $8\cdot \sqrt{2^n/n}$ threshold gates as sufficient for a small error rate, where $n := \log|{\mathcal S}_L|$. en dc.language.iso eng dc.relation.ispartof International Journal on Artificial Intelligence Tools dc.title A Computational Study on Circuit Size vs. Circuit Depth en dc.contributor.institution School of Computer Science dc.description.status Peer reviewed dc.relation.school School of Computer Science dcterms.dateAccepted 2006 rioxxterms.versionofrecord https://doi.org/10.1142/S0218213006002606 rioxxterms.type Journal Article/Review herts.preservation.rarelyaccessed true
﻿

## Files in this item

FilesSizeFormatView

There are no files associated with this item.