000 02288nam a22003618i 4500
001 CR9780511569920
003 UkCbUP
005 20200124160231.0
006 m|||||o||d||||||||
007 cr||||||||||||
008 090520s1998||||enk o ||1 0|eng|d
020 _a9780511569920 (ebook)
020 _z9780521652636 (hardback)
020 _z9780521117913 (paperback)
040 _aUkCbUP
_beng
_erda
_cUkCbUP
050 0 0 _aQA76.87
_b.O5 1998
082 0 0 _a006.3/2
_221
245 0 0 _aOn-line learning in neural networks /
_cedited by David Saad.
264 1 _aCambridge :
_bCambridge University Press,
_c1998.
300 _a1 online resource (x, 398 pages) :
_bdigital, PDF file(s).
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
490 1 _aPublications of the Newton Institute ;
_v17
500 _aTitle from publisher's bibliographic system (viewed on 05 Oct 2015).
520 _aOn-line learning is one of the most powerful and commonly used techniques for training large layered networks and has been used successfully in many real-world applications. Traditional analytical methods have been recently complemented by ones from statistical physics and Bayesian statistics. This powerful combination of analytical methods provides more insight and deeper understanding of existing algorithms and leads to novel and principled proposals for their improvement. This book presents a coherent picture of the state-of-the-art in the theoretical analysis of on-line learning. An introduction relates the subject to other developments in neural networks and explains the overall picture. Surveys by leading experts in the field combine new and established material and enable non-experts to learn more about the techniques and methods used. This book, the first in the area, provides a comprehensive view of the subject and will be welcomed by mathematicians, scientists and engineers, whether in industry or academia.
650 0 _aNeural networks (Computer science)
650 0 _aComputer networks.
700 1 _aSaad, David,
_eeditor.
776 0 8 _iPrint version:
_z9780521652636
830 0 _aPublications of the Newton Institute ;
_v17.
856 4 0 _uhttps://doi.org/10.1017/CBO9780511569920
999 _c517631
_d517629