Analog VLSI Integration of Massive Parallel Signal Processing Systems
General Material Designation
[Book]
First Statement of Responsibility
by Peter Kinget, Michiel Steyaert.
.PUBLICATION, DISTRIBUTION, ETC
Place of Publication, Distribution, etc.
Boston, MA :
Name of Publisher, Distributor, etc.
Imprint: Springer,
Date of Publication, Distribution, etc.
1997.
SERIES
Series Title
Springer International Series in Engineering and Computer Science,
Volume Designation
384
ISSN of Series
0893-3405 ;
CONTENTS NOTE
Text of Note
1. Analog Parallel Signal Processing -- 2. Implications of Mismatch on Analog VLSI -- 3. Implementation Oriented Theory for CNN's -- 4. VLSI Implementation of CNN's -- 5. General Conclusions -- Appendices -- A- MOS transistor models.
0
SUMMARY OR ABSTRACT
Text of Note
When comparing conventional computing architectures to the architectures of biological neural systems, there are several striking differences. Conventional computers use a low number of high performance computing elements that are programmed with algorithms to perform tasks in a time sequenced way; they are very successful in administrative applications, in scientific simulations, and in certain signal processing applications. However, the biological systems still significantly outperform conventional computers in perception tasks, sensory data processing and motory control. Biological systems use a completely different computing paradigm: a massive network of simple processors that are (adaptively) interconnected and operate in parallel. This massively parallel processing seems the key aspect to their success. The advent of VLSI technologies has provided us with the technological means to implement very complicated systems on a silicon die. Analog VLSI circuits in standard digital technologies open the way for the implementation of massively parallel analog signal processing systems for sensory signal processing applications and for perception tasks. Analog VLSI Integration of Massive Parallel Processing Systems describes in depth the theory and practice of designing these massively parallel analog signal processing systems. Techniques are described which overcome the device and transistor mismatches which limit performance of the system. The book also shows how such a system can be efficiently implemented using cellular Neural Networks. Analog VLSI Integration of Massive Parallel Processing Systems is essential reading for practicing analog design engineers and researchers in the field. It is also suitable as a text for an advanced course on the subject.