A computational study on circuit size versus circuit depth

Lappas, G., Frank, R. J. and Albrecht, Andreas A. (2006) A computational study on circuit size versus circuit depth. International Journal on Artificial Intelligence Tools, 15 (2). pp. 143-162. ISSN 0218-2130 (doi:10.1142/S0218213006002606)

Full text is not in this repository.

Abstract

[Please see the article via the link above for the full abstract including mathematical formulae]. 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. 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.

Item Type: Article
Keywords (uncontrolled): Machine learning; circuit complexity; simulated annealing
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 12385
Depositing User: Andreas Albrecht
Date Deposited: 08 Nov 2013 09:18
Last Modified: 12 Jun 2019 12:37
URI: https://eprints.mdx.ac.uk/id/eprint/12385

Actions (login required)

Edit Item Edit Item