Název:
Representations of Boolean Functions by Perceptron Networks
Autoři:
Kůrková, Věra Typ dokumentu: Příspěvky z konference Konference/Akce: ITAT 2014. European Conference on Information Technologies - Applications and Theory /14./, Demänovská dolina (SK), 2014-09-25 / 2014-09-29
Rok:
2014
Jazyk:
eng
Abstrakt: 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
Klíčová slova:
Boolean functions; model complexity; perceptron networks Číslo projektu: LD13002 (CEP) Poskytovatel projektu: GA MŠk Zdrojový dokument: ITAT 2014. Information Technologies - Applications and Theory. Part II, ISBN 978-80-87136-19-5
Instituce: Ústav informatiky AV ČR
(web)
Informace o dostupnosti dokumentu:
Dokument je dostupný v repozitáři Akademie věd. Původní záznam: http://hdl.handle.net/11104/0236782