Original title: Representations of Boolean Functions by Perceptron Networks
Authors: Kůrková, Věra
Document type: Papers
Conference/Event: ITAT 2014. European Conference on Information Technologies - Applications and Theory /14./, Demänovská dolina (SK), 2014-09-25 / 2014-09-29
Year: 2014
Language: eng
Abstract: Limitations of capabilities of shallow perceptron networks are investigated. Lower bounds are derived for growth of numbers of units and sizes of output weights in networks representing Boolean functions of d variables. It is shown that for large d, almost any randomly chosen Boolean function cannot be tractably represented by shallow perceptron networks, i.e., each its representation requires a network with number of units or sizes of output weights depending on d exponentially
Keywords: Boolean functions; model complexity; perceptron networks
Project no.: LD13002 (CEP)
Funding provider: GA MŠk
Host item entry: ITAT 2014. Information Technologies - Applications and Theory. Part II, ISBN 978-80-87136-19-5

Institution: Institute of Computer Science AS ČR (web)
Document availability information: Fulltext is available in the digital repository of the Academy of Sciences.
Original record: http://hdl.handle.net/11104/0236782

Permalink: http://www.nusl.cz/ntk/nusl-175463


The record appears in these collections:
Research > Institutes ASCR > Institute of Computer Science
Conference materials > Papers