Neural Networks And Systolic Array Design

Neural networks (NNs) and systolic arrays (SAs) have many similar features. This volume describes, in a unified way, the basic concepts, theories and characteristic features of integrating or formulating different facets of NNs and SAs, as well as presents recent developments and significant applications. The articles, written by experts from all over the world, demonstrate the various ways this integration can be made to efficiently design methodologies, algorithms and architectures, and also implementations, for NN applications. The book will be useful to graduate students and researchers in many related areas, not only as a reference book but also as a textbook for some parts of the curriculum. It will also benefit researchers and practitioners in industry and R&D laboratories who are working in the fields of system design, VLSI, parallel processing, neural networks, and vision.

This is Volume III of a three volume set constituting the refereed proceedings of the Third International Symposium on Neural Networks, ISNN 2006. 616 revised papers are organized in topical sections on neurobiological analysis, theoretical analysis, neurodynamic optimization, learning algorithms, model design, kernel methods, data preprocessing, pattern classification, computer vision, image and signal processing, system modeling, robotic systems, transportation systems, communication networks, information security, fault detection, financial analysis, bioinformatics, biomedical and industrial applications, and more.

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.

This book provides a structured treatment of the key principles and techniques for enabling efficient processing of deep neural networks (DNNs). DNNs are currently widely used for many artificial intelligence (AI) applications, including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at the cost of high computational complexity. Therefore, techniques that enable efficient processing of deep neural networks to improve key metrics—such as energy-efficiency, throughput, and latency—without sacrificing accuracy or increasing hardware costs are critical to enabling the wide deployment of DNNs in AI systems. The book includes background on DNN processing; a description and taxonomy of hardware architectural approaches for designing DNN accelerators; key metrics for evaluating and comparing different designs; features of DNN processing that are amenable to hardware/algorithm co-design to improve energy efficiency and throughput; and opportunities for applying new technologies. Readers will find a structured introduction to the field as well as formalization and organization of key concepts from contemporary work that provide insights that may spark new ideas.

This collection of recent studies spans a range of computational intelligence applications, emphasizing their application to challenging real-world problems. Covers Intelligent agent-based algorithms, Hybrid intelligent systems, Machine learning and more.

Content Description #Includes bibliographical references and index.