000			03311nam a2200505 i 4500
001			6267497
003			IEEE
005			20220712204723.0
006			m o d
007			cr |n|||||||||
008			151223s1993 maua ob 001 eng d
010			_z 93010027 (print)
020			_z9780262140546 _qprint
020			_a9780262290937 _qelectronic
020			_z0262140543 _qprint
035			_a(CaBNVSL)mat06267497
035			_a(IDAMS)0b000064818b450b
040			_aCaBNVSL _beng _erda _cCaBNVSL _dCaBNVSL
050		4	_aQA76.87 _b.N5 1993eb
082	0	0	_a006.4/2 _220
100	1		_aNigrin, Albert, _eauthor. _923128
245	1	0	_aNeural networks for pattern recognition / _cAlbert Nigrin.
264		1	_aCambridge, Massachusetts : _bMIT Press, _cc1993.
264		2	_a[Piscataqay, New Jersey] : _bIEEE Xplore, _c[1993]
300			_a1 PDF (xvii, 413 pages) : _billustrations.
336			_atext _2rdacontent
337			_aelectronic _2isbdmedia
338			_aonline resource _2rdacarrier
500			_a"A Bradford book."
504			_aIncludes bibliographical references (p. [399]-405) and index.
506	1		_aRestricted to subscribers or individual electronic text purchasers.
520			_aNeural Networks for Pattern Recognition takes the pioneering work in artificial neural networks by Stephen Grossberg and his colleagues to a new level. In a simple and accessible way it extends embedding field theory into areas of machine intelligence that have not been clearly dealt with before. Following a tutorial of existing neural networks for pattern classification, Nigrin expands on these networks to present fundamentally new architectures that perform realtime pattern classification of embedded and synonymous patterns and that will aid in tasks such as vision, speech recognition, sensor fusion, and constraint satisfaction.Nigrin presents the new architectures in two stages. First he presents a network called Sonnet 1 that already achieves important properties such as the ability to learn and segment continuously varied input patterns in real time, to process patterns in a context sensitive fashion, and to learn new patterns without degrading existing categories. He then removes simplifications inherent in Sonnet 1 and introduces radically new architectures. These architectures have the power to classify patterns that may have similar meanings but that have different external appearances (synonyms). They also have been designed to represent patterns in a distributed fashion, both in short-term and long-term memory.Albert Nigrin is Assistant Professor in the Department of Computer Science and Information Systems at American University.
530			_aAlso available in print.
538			_aMode of access: World Wide Web
588			_aDescription based on PDF viewed 12/23/2015.
650		0	_aNeural networks (Computer science) _93414
650		0	_aPattern recognition systems. _93953
650		0	_aSelf-organizing systems. _923129
655		0	_aElectronic books. _93294
710	2		_aIEEE Xplore (Online Service), _edistributor. _923130
710	2		_aMIT Press, _epublisher. _923131
776	0	8	_iPrint version _z9780262140546
856	4	2	_3Abstract with links to resource _uhttps://ieeexplore.ieee.org/xpl/bkabstractplus.jsp?bkn=6267497
942			_cEBK
999			_c73151 _d73151