000			02215nam a22003738i 4500
001			CR9780511626258
003			UkCbUP
005			20200124160304.0
006			m|||||o||d||||||||
007			cr||||||||||||
008			090916s1996||||enk o ||1 0|eng|d
020			_a9780511626258 (ebook)
020			_z9780521445320 (hardback)
020			_z9781107402843 (paperback)
040			_aUkCbUP _beng _erda _cUkCbUP
050	0	0	_aQ335 _b.A88 1996
082	0	0	_a006.3 _220
100	1		_aAubin, Jean Pierre, _eauthor.
245	1	0	_aNeural networks and qualitative physics / _cJean-Pierre Aubin.
246	3		_aNeural Networks & Qualitative Physics
264		1	_aCambridge : _bCambridge University Press, _c1996.
300			_a1 online resource (xvii, 283 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			_aOriginally published in 1996, this book is devoted to some mathematical methods that arise in two domains of artificial intelligence: neural networks and qualitative physics. Professor Aubin makes use of control and viability theory in neural networks and cognitive systems, regarded as dynamical systems controlled by synaptic matrices, and set-valued analysis that plays a natural and crucial role in qualitative analysis and simulation. This allows many examples of neural networks to be presented in a unified way. In addition, several results on the control of linear and nonlinear systems are used to obtain a 'learning algorithm' of pattern classification problems, such as the back-propagation formula, as well as learning algorithms of feedback regulation laws of solutions to control systems subject to state constraints. This book will be of value to anyone with an interest in neural networks and cognitive systems.
650		0	_aArtificial intelligence _xMathematics.
650		0	_aNeural networks.
650		0	_aNeural networks (Computer science)
650		0	_aMathematical physics.
776	0	8	_iPrint version: _z9780521445320
856	4	0	_uhttps://doi.org/10.1017/CBO9780511626258
999			_c520603 _d520601