000 02254nam a22003378i 4500
001 CR9780511624216
003 UkCbUP
005 20200124160251.0
006 m|||||o||d||||||||
007 cr||||||||||||
008 090916s1999||||enk o ||1 0|eng|d
020 _a9780511624216 (ebook)
020 _z9780521573535 (hardback)
020 _z9780521118620 (paperback)
040 _aUkCbUP
_beng
_erda
_cUkCbUP
050 0 0 _aQA76.87
_b.A58 1999
082 0 0 _a006.3/2
_221
100 1 _aAnthony, Martin,
_eauthor.
245 1 0 _aNeural network learning :
_btheoretical foundations /
_cMartin Anthony and Peter L. Bartlett.
264 1 _aCambridge :
_bCambridge University Press,
_c1999.
300 _a1 online resource (xiv, 389 pages) :
_bdigital, PDF file(s).
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
500 _aTitle from publisher's bibliographic system (viewed on 05 Oct 2015).
520 _aThis book describes theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key statistical and computational questions. Research on pattern classification with binary-output networks is surveyed, including a discussion of the relevance of the Vapnik-Chervonenkis dimension, and calculating estimates of the dimension for several neural network models. A model of classification by real-output networks is developed, and the usefulness of classification with a 'large margin' is demonstrated. The authors explain the role of scale-sensitive versions of the Vapnik-Chervonenkis dimension in large margin classification, and in real prediction. They also discuss the computational complexity of neural network learning, describing a variety of hardness results, and outlining two efficient constructive learning algorithms. The book is self-contained and is intended to be accessible to researchers and graduate students in computer science, engineering, and mathematics.
650 0 _aNeural networks (Computer science)
700 1 _aBartlett, Peter L.,
_d1966-
_eauthor.
776 0 8 _iPrint version:
_z9780521573535
856 4 0 _uhttps://doi.org/10.1017/CBO9780511624216
999 _c519499
_d519497