Adaptive Analog VLSI Neural Systems is the first practical book on neural networks learning chips and systems. It covers the entire process of implementing neural networks in VLSI chips, beginning with the crucial issues of learning algorithms in an analog framework and limited precision effects, and giving actual case studies of working systems. The approach is systems and applications oriented throughout, demonstrating the attractiveness of such an approach for applications such as adaptive pattern recognition and optical character recognition. Dr Jabri and his co-authors from AT&T Bell Laboratories, Bellcore and the University of Sydney provide a comprehensive introduction to VLSI neural networks suitable for research and development staff and advanced students.

This volume contains the proceedings of a workshop on Analog Integrated Neural Systems held May 8, 1989, in connection with the International Symposium on Circuits and Systems. The presentations were chosen to encompass the entire range of topics currently under study in this exciting new discipline. Stringent acceptance requirements were placed on contributions: (1) each description was required to include detailed characterization of a working chip, and (2) each design was not to have been published previously. In several cases, the status of the project was not known until a few weeks before the meeting date. As a result, some of the most recent innovative work in the field was presented. Because this discipline is evolving rapidly, each project is very much a work in progress. Authors were asked to devote considerable attention to the shortcomings of their designs, as well as to the notable successes they achieved. In this way, other workers can now avoid stumbling into the same traps, and evolution can proceed more rapidly (and less painfully). The chapters in this volume are presented in the same order as the corresponding presentations at the workshop. The first two chapters are concerned with fmding solutions to complex optimization problems under a predefmed set of constraints. The first chapter reports what is, to the best of our knowledge, the first neural-chip design. In each case, the physics of the underlying electronic medium is used to represent a cost function in a natural way, using only nearest-neighbor connectivity.

Learning on Silicon combines models of adaptive information processing in the brain with advances in microelectronics technology and circuit design. The premise is to construct integrated systems not only loaded with sufficient computational power to handle demanding signal processing tasks in sensory perception and pattern recognition, but also capable of operating autonomously and robustly in unpredictable environments through mechanisms of adaptation and learning. This edited volume covers the spectrum of Learning on Silicon in five parts: adaptive sensory systems, neuromorphic learning, learning architectures, learning dynamics, and learning systems. The 18 chapters are documented with examples of fabricated systems, experimental results from silicon, and integrated applications ranging from adaptive optics to biomedical instrumentation. As the first comprehensive treatment on the subject, Learning on Silicon serves as a reference for beginners and experienced researchers alike. It provides excellent material for an advanced course, and a source of inspiration for continued research towards building intelligent adaptive machines.

This book brings together in one place important contributions and state-of-the-art research in the rapidly advancing area of analog VLSI neural networks. The book serves as an excellent reference, providing insights into some of the most important issues in analog VLSI neural networks research efforts.

A self-contained text, suitable for a broad audience. Presents basic concepts in electronics, transistor physics, and neurobiology for readers without backgrounds in those areas. Annotation copyrighted by Book News, Inc., Portland, OR

Research presented in this thesis provides a substantial leap from the study of interesting device physics to fully adaptive analog networks and lays a solid foundation for future development of large-scale, compact, low-power adaptive parallel analog computation systems. The investigation described here started with observation of this potential learning capability and led to the first derivation and characterization of the floating-gate pFET correlation learning rule. Starting with two synapses sharing the same error signal, we progressed from phase correlation experiments through correlation experiments involving harmonically related sinusoids, culminating in learning the Fourier series coefficients of a square wave cite. Extending these earlier two-input node experiments to the general case of correlated inputs required dealing with weight decay naturally exhibited by the learning rule. We introduced a source-follower floating-gate synapse as an improvement over our earlier source-degenerated floating-gate synapse in terms of relative weight decay cite. A larger network of source-follower floating-gate synapses was fabricated and an FPGA-controlled testboard was designed and built. This more sophisticated system provides an excellent framework for exploring applications to multi-input, multi-node adaptive filtering applications. Adaptive channel equalization provided a practical test-case illustrating the use of these adaptive systems in solving real-world problems. The same system could easily be applied to noise and echo cancellation in communication systems and system identification tasks in optimal control problems. We envision the commercialization of these adaptive analog VLSI systems as practical products within a couple of years.

Although it is now possible to integrate many millions of transistors on a single chip, traditional digital circuit technology is now reaching its limits, facing problems of cost and technical efficiency when scaled down to ever-smaller feature sizes. The analysis of biological neural systems, especially for visual processing, has allowed engineers to better understand how complex networks can effectively process large amounts of information, whilst dealing with difficult computational challenges. Analog and parallel processing are key characteristics of biological neural networks. Analog VLSI circuits using the same features can therefore be developed to emulate brain-style processing. Using standard CMOS technology, they can be cheaply manufactured, permitting efficient industrial and consumer applications in robotics and mobile electronics. This book explores the theory, design and implementation of analog VLSI circuits, inspired by visual motion processing in biological neural networks. Using a novel approach pioneered by the author himself, Stocker explains in detail the construction of a series of electronic chips, providing the reader with a valuable practical insight into the technology. Analog VLSI Circuits for the Perception of Visual Motion: analyses the computational problems in visual motion perception; examines the issue of optimization in analog networks through high level processes such as motion segmentation and selective attention; demonstrates network implementation in analog VLSI CMOS technology to provide computationally efficient devices; sets out measurements of final hardware implementation; illustrates the similarities of the presented circuits with the human visual motion perception system; includes an accompanying website with video clips of circuits under real-time visual conditions and additional supplementary material. With a complete review of all existing neuromorphic analog VLSI systems for visual motion sensing, Analog VLSI Circuits for the Perception of Visual Motion is a unique reference for advanced students in electrical engineering, artificial intelligence, robotics and computational neuroscience. It will also be useful for researchers, professionals, and electronics engineers working in the field.

The early era of neural network hardware design (starting at 1985) was mainly technology driven. Designers used almost exclusively analog signal processing concepts for the recall mode. Learning was deemed not to cause a problem because the number of implementable synapses was still so low that the determination of weights and thresholds could be left to conventional computers. Instead, designers tried to directly map neural parallelity into hardware. The architectural concepts were accordingly simple and produced the so called interconnection problem which, in turn, made many engineers believe it could be solved by optical implementation in adequate fashion only. Furthermore, the inherent fault-tolerance and limited computation accuracy of neural networks were claimed to justify that little effort is to be spend on careful design, but most effort be put on technology issues. As a result, it was almost impossible to predict whether an electronic neural network would function in the way it was simulated to do. This limited the use of the first neuro-chips for further experimentation, not to mention that real-world applications called for much more synapses than could be implemented on a single chip at that time. Meanwhile matters have matured. It is recognized that isolated definition of the effort of analog multiplication, for instance, would be just as inappropriate on the part ofthe chip designer as determination of the weights by simulation, without allowing for the computing accuracy that can be achieved, on the part of the user.

Engineers have long been fascinated by how efficient and how fast biological neural networks are capable of performing such complex tasks as recognition. Such networks are capable of recognizing input data from any of the five senses with the necessary accuracy and speed to allow living creatures to survive. Machines which perform such complex tasks as recognition, with similar ac curacy and speed, were difficult to implement until the technological advances of VLSI circuits and systems in the late 1980's. Since then, the field of VLSI Artificial Neural Networks (ANNs) have witnessed an exponential growth and a new engineering discipline was born. Today, many engineering curriculums have included a course or more on the subject at the graduate or senior under graduate levels. Since the pioneering book by Carver Mead; "Analog VLSI and Neural Sys tems", Addison-Wesley, 1989; there were a number of excellent text and ref erence books on the subject, each dealing with one or two topics. This book attempts to present an integrated approach of a single research team to VLSI ANNs Engineering.