Neural networks for pattern recognition

"Neural Networks for Pattern Recognition takes to a new level the pioneering work in artificial neural networks by Stephen Grossberg and his colleagues. In a simple and accessible way it extends embedding field theory into areas of machine intelligence that have not been clearly dealt with befo...

Full description

Saved in:
Bibliographic Details
Main Author: Nigrin, Albert.
Format: eBook
Language: English
Published: Cambridge, Mass. : MIT Press, c1993.
Subjects:
Neural networks (Computer science)
Pattern recognition systems.
Self-organizing systems.
elektronické knihy
electronic books
ISBN: 9780262290937
Physical Description: 1 online zdroj (xvii, 413 p.) : ill.

Cover

Table of contents

LEADER 03309cam a2200361 a 4500
001 74952
003 CZ ZlUTB
005 20240911212319.0
006 m d
007 cr un
008 130208s1993 maua sb 001 0 eng d
020 |a 9780262290937  |q (ebook) 
035 |a (OCoLC)827009335 
040 |a IEEEE  |c IEEEE  |d OCLCF 
100 1 |a Nigrin, Albert. 
245 1 0 |a Neural networks for pattern recognition  |h [elektronický zdroj] /  |c Albert Nigrin. 
260 |a Cambridge, Mass. :  |b MIT Press,  |c c1993. 
300 |a 1 online zdroj (xvii, 413 p.) :  |b ill. 
500 |a "A Bradford book." 
504 |a Includes bibliographical references (p. [399]-405) and index. 
505 0 |a Introduction -- Highlights of adaptive resonance theory -- Classifying spatial patterns -- Classifying temporal patterns -- Multilayer networks and the use of attention -- Representing synonyms -- Specific architectures that use presynaptic inhibition -- Conclusion -- A. Feedforward circuits for normalization and noise suppression -- B. Network Equations used in the simulations of chapter 3 -- C. Network equations used in the simulations of chapter 4. 
520 |a "Neural Networks for Pattern Recognition takes to a new level the pioneering work in artificial neural networks by Stephen Grossberg and his colleagues. 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 real-time 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."--BOOK JACKET. 
506 |a Plný text je dostupný pouze z IP adres počítačů Univerzity Tomáše Bati ve Zlíně nebo vzdáleným přístupem pro zaměstnance a studenty univerzity 
650 0 |a Neural networks (Computer science) 
650 0 |a Pattern recognition systems. 
650 0 |a Self-organizing systems. 
655 7 |a elektronické knihy  |7 fd186907  |2 czenas 
655 9 |a electronic books  |2 eczenas 
776 0 8 |i Print version:  |a Nigrin, Albert.  |t Neural networks for pattern recognition.  |d Cambridge, Mass. : MIT Press, c1993  |z 0262140543  |w (DLC) 93010027  |w (OCoLC)27768477 
856 4 0 |u https://proxy.k.utb.cz/login?url=http://ieeexplore.ieee.org/xpl/bkabstractplus.jsp?bkn=6267497  |y Plný text 
992 |a BK  |c EBOOK-TN  |c MITPRESS 
999 |c 74952  |d 74952 
993 |x NEPOSILAT  |y EIZ 

Similar Items