A note on a priori estimations of classification circuit complexity

Albrecht, Andreas A., Chashkin, Alexander V., Iliopoulos, Costas S., Kasim-Zade, Oktay M., Lappas, Georgios and Steinhofel, Kathleen K. (2010) A note on a priori estimations of classification circuit complexity. Fundamenta Informaticae, 104 (3) . pp. 201-217. ISSN 0169-2968 [Article] (doi:10.3233/FI-2010-344)


The paper aims at tight upper bounds on the size of pattern classification circuits that can be used for a priori parameter settings in a machine learning context. The upper bounds relate the circuit size S(C) to nL := [log2mL], where mL is the number of training samples. In particular, we show that there exist unbounded fan-in threshold circuits with less than (a) SRcc := 2·√2nL + 3 gates for unbounded depth, (b) SLcc := 34.8 · √2nL + 14 · nL − 11 · log2nL + 2 gates for small bounded depth, where in both cases all mL samples are classified correctly. We note that the upper bounds do not depend on the length n of input (sample) vectors. Since nL << n in real-world problem settings, the upper bounds return values that are suitable for practical applications. We provide experimental evidence that the circuit size estimations work well on a number of pattern classification tasks. As a result, we formulate the conjecture that [1.25 · SRcc or [0.07 · SLcc] gates are sufficient to achieve a high generalization rate of bounded-depth classification circuits.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 12394
Depositing User: Andreas Albrecht
Date Deposited: 08 Nov 2013 08:33
Last Modified: 22 Sep 2022 17:50
URI: https://eprints.mdx.ac.uk/id/eprint/12394

Actions (login required)

View Item View Item


Activity Overview
6 month trend
6 month trend

Additional statistics are available via IRStats2.