#### Zhiyuan Liu Introduction to Graph Neural Networks

Graphs are useful data structures in complex real-life applications such as modeling physical systems, learning molecular fingerprints, controlling traffic networks, and recommending friends in social networks. However, these tasks require dealing with non-Euclidean graph data that contains rich relational information between elements and cannot be well handled by traditional deep learning models (e.g., convolutional neural networks (CNNs) or recurrent neural networks (RNNs)). Nodes in graphs usually contain useful feature information that cannot be well addressed in most unsupervised representation learning methods (e.g., network embedding methods). Graph neural networks (GNNs) are proposed to combine the feature information and the graph structure to learn better representations on graphs via feature propagation and aggregation. Due to its convincing performance and high interpretability, GNN has recently become a widely applied graph analysis tool. This book provides a comprehensive introduction to the basic concepts, models, and applications of graph neural networks. It starts with the introduction of the vanilla GNN model. Then several variants of the vanilla model are introduced such as graph convolutional networks, graph recurrent networks, graph attention networks, graph residual networks, and several general frameworks. Variants for different graph types and advanced training methods are also included. As for the applications of GNNs, the book categorizes them into structural, non-structural, and other scenarios, and then it introduces several typical models on solving these tasks. Finally, the closing chapters provide GNN open resources and the outlook of several future directions.

/ / похожие

Подробнее#### Gene Cheung Graph Spectral Image Processing

Graph spectral image processing is the study of imaging data from a graph frequency perspective. Modern image sensors capture a wide range of visual data including high spatial resolution/high bit-depth 2D images and videos, hyperspectral images, light field images and 3D point clouds. The field of graph signal processing – extending traditional Fourier analysis tools such as transforms and wavelets to handle data on irregular graph kernels – provides new flexible computational tools to analyze and process these varied types of imaging data. Recent methods combine graph signal processing ideas with deep neural network architectures for enhanced performances, with robustness and smaller memory requirements.<br /><br />The book is divided into two parts. The first is centered on the fundamentals of graph signal processing theories, including graph filtering, graph learning and graph neural networks. The second part details several imaging applications using graph signal processing tools, including image and video compression, 3D image compression, image restoration, point cloud processing, image segmentation and image classification, as well as the use of graph neural networks for image processing.

/ / похожие

Подробнее#### Albert Chun-Chen Liu Artificial Intelligence Hardware Design

ARTIFICIAL INTELLIGENCE HARDWARE DESIGN Learn foundational and advanced topics in Neural Processing Unit design with real-world examples from leading voices in the field In Artificial Intelligence Hardware Design: Challenges and Solutions , distinguished researchers and authors Drs. Albert Chun Chen Liu and Oscar Ming Kin Law deliver a rigorous and practical treatment of the design applications of specific circuits and systems for accelerating neural network processing. Beginning with a discussion and explanation of neural networks and their developmental history, the book goes on to describe parallel architectures, streaming graphs for massive parallel computation, and convolution optimization. The authors offer readers an illustration of in-memory computation through Georgia Tech’s Neurocube and Stanford’s Tetris accelerator using the Hybrid Memory Cube, as well as near-memory architecture through the embedded eDRAM of the Institute of Computing Technology, the Chinese Academy of Science, and other institutions. Readers will also find a discussion of 3D neural processing techniques to support multiple layer neural networks, as well as information like: A thorough introduction to neural networks and neural network development history, as well as Convolutional Neural Network (CNN) models Explorations of various parallel architectures, including the Intel CPU, Nvidia GPU, Google TPU, and Microsoft NPU, emphasizing hardware and software integration for performance improvement Discussions of streaming graph for massive parallel computation with the Blaize GSP and Graphcore IPU An examination of how to optimize convolution with UCLA Deep Convolutional Neural Network accelerator filter decomposition Perfect for hardware and software engineers and firmware developers, Artificial Intelligence Hardware Design is an indispensable resource for anyone working with Neural Processing Units in either a hardware or software capacity.

/ / похожие

Подробнее#### Michael Stiebitz Graph Edge Coloring

Features recent advances and new applications in graph edge coloring Reviewing recent advances in the Edge Coloring Problem, Graph Edge Coloring: Vizing's Theorem and Goldberg's Conjecture provides an overview of the current state of the science, explaining the interconnections among the results obtained from important graph theory studies. The authors introduce many new improved proofs of known results to identify and point to possible solutions for open problems in edge coloring. The book begins with an introduction to graph theory and the concept of edge coloring. Subsequent chapters explore important topics such as: Use of Tashkinov trees to obtain an asymptotic positive solution to Goldberg's conjecture Application of Vizing fans to obtain both known and new results Kierstead paths as an alternative to Vizing fans Classification problem of simple graphs Generalized edge coloring in which a color may appear more than once at a vertex This book also features first-time English translations of two groundbreaking papers written by Vadim Vizing on an estimate of the chromatic class of a p-graph and the critical graphs within a given chromatic class. Written by leading experts who have reinvigorated research in the field, Graph Edge Coloring is an excellent book for mathematics, optimization, and computer science courses at the graduate level. The book also serves as a valuable reference for researchers interested in discrete mathematics, graph theory, operations research, theoretical computer science, and combinatorial optimization.

/ / похожие

Подробнее#### SOP20-DIP20 ZLG ZHIYUAN Programmer Adapter ZY301A Apply to SOP20/SOP18/SOP16/SOP14/SOP8 (200mil)

#### Yoav Goldberg Neural Network Methods in Natural Language Processing

Neural networks are a family of powerful machine learning models. This book focuses on the application of neural network models to natural language data. The first half of the book (Parts I and II) covers the basics of supervised machine learning and feed-forward neural networks, the basics of working with machine learning over language data, and the use of vector-based rather than symbolic representations for words. It also covers the computation-graph abstraction, which allows to easily define and train arbitrary neural networks, and is the basis behind the design of contemporary neural network software libraries. The second part of the book (Parts III and IV) introduces more specialized neural network architectures, including 1D convolutional neural networks, recurrent neural networks, conditioned-generation models, and attention-based models. These architectures and techniques are the driving force behind state-of-the-art algorithms for machine translation, syntactic parsing, and many other applications. Finally, we also discuss tree-shaped networks, structured prediction, and the prospects of multi-task learning.

/ / похожие

Подробнее#### Stanislaw Zak H. An Introduction to Optimization

A modern, up-to-date introduction to optimization theory and methods This authoritative book serves as an introductory text to optimization at the senior undergraduate and beginning graduate levels. With consistently accessible and elementary treatment of all topics, An Introduction to Optimization, Second Edition helps students build a solid working knowledge of the field, including unconstrained optimization, linear programming, and constrained optimization. Supplemented with more than one hundred tables and illustrations, an extensive bibliography, and numerous worked examples to illustrate both theory and algorithms, this book also provides: * A review of the required mathematical background material * A mathematical discussion at a level accessible to MBA and business students * A treatment of both linear and nonlinear programming * An introduction to recent developments, including neural networks, genetic algorithms, and interior-point methods * A chapter on the use of descent algorithms for the training of feedforward neural networks * Exercise problems after every chapter, many new to this edition * MATLAB(r) exercises and examples * Accompanying Instructor's Solutions Manual available on request An Introduction to Optimization, Second Edition helps students prepare for the advanced topics and technological developments that lie ahead. It is also a useful book for researchers and professionals in mathematics, electrical engineering, economics, statistics, and business. An Instructor's Manual presenting detailed solutions to all the problems in the book is available from the Wiley editorial department.

/ / похожие

Подробнее#### Группа авторов Handbook of Neural Engineering

An important new work establishing a foundation for future developments in neural engineering The Handbook of Neural Engineering provides theoretical foundations in computational neural science and engineering and current applications in wearable and implantable neural sensors/probes. Inside, leading experts from diverse disciplinary groups representing academia, industry, and private and government organizations present peer-reviewed contributions on the brain-computer interface, nano-neural engineering, neural prostheses, imaging the brain, neural signal processing, the brain, and neurons. The Handbook of Neural Engineering covers: Neural signal and image processing–the analysis and modeling of neural activity and EEG-related activities using the nonlinear and nonstationary analysis methods, including the chaos, fractal, and time-frequency and time-scale analysis methods–and how to measure functional, physiological, and metabolic activities in the human brain using current and emerging medical imaging technologies Neuro-nanotechnology, artificial implants, and neural prosthesis–the design of multi-electrode arrays to study how the neurons of human and animals encode stimuli, the evaluation of functional changes in neural networks after stroke and spinal cord injuries, and improvements in therapeutic applications using neural prostheses Neurorobotics and neural rehabilitation engineering–the recent developments in the areas of biorobotic system, biosonar head, limb kinematics, and robot-assisted activity to improve the treatment of elderly subjects at the hospital and home, as well as the interactions of the neuron chip, neural information processing, perception and neural dynamics, learning memory and behavior, biological neural networks, and neural control

/ / похожие

Подробнее#### Xiaoyu Cai Formation Control of Multi-Agent Systems. A Graph Rigidity Approach

Formation Control of Multi-Agent Systems: A Graph Rigidity Approach Marcio de Queiroz, Louisiana State University, USA Xiaoyu Cai, FARO Technologies, USA Matthew Feemster, U.S. Naval Academy, USA A comprehensive guide to formation control of multi-agent systems using rigid graph theory This book is the first to provide a comprehensive and unified treatment of the subject of graph rigidity-based formation control of multi-agent systems. Such systems are relevant to a variety of emerging engineering applications, including unmanned robotic vehicles and mobile sensor networks. Graph theory, and rigid graphs in particular, provides a natural tool for describing the multi-agent formation shape as well as the inter-agent sensing, communication, and control topology. Beginning with an introduction to rigid graph theory, the contents of the book are organized by the agent dynamic model (single integrator, double integrator, and mechanical dynamics) and by the type of formation problem (formation acquisition, formation manoeuvring, and target interception). The book presents the material in ascending level of difficulty and in a self-contained manner; thus, facilitating reader understanding. Key features: Uses the concept of graph rigidity as the basis for describing the multi-agent formation geometry and solving formation control problems. Considers different agent models and formation control problems. Control designs throughout the book progressively build upon each other. Provides a primer on rigid graph theory. Combines theory, computer simulations, and experimental results. Formation Control of Multi-Agent Systems: A Graph Rigidity Approach is targeted at researchers and graduate students in the areas of control systems and robotics. Prerequisite knowledge includes linear algebra, matrix theory, control systems, and nonlinear systems.

/ / похожие

Подробнее#### J. Peter Dosch Manual of Neural Therapy According to Huneke

More and more patients with chronic pain and other disorders are relying on neural therapy – a treatment concept based on employing the properties of local anesthetics to regulate disorders of the autonomic system – to alleviate their symptoms. Yet there are precious few spezialized, didactic resources for medical practitioners interested in learning about this highly effective therapeutic alternative.The <strong><i>Manual of Neural Therapy According to Huneke</i></strong> offers accessible, practical information on all aspects of neural therapy as it is practiced today. Designed for use in the classroom and in the clinic, this illustrated manual comprises three sections:– Theory and Practice of neural therapy according to Huneke – including detailed definitions of all terminology; discussions of experiments, successes, and failures of neural therapy; the scientific theory behind segmental therapy and interference fields; and practical applications.– Encyclopedia of neural therapy – featuring an encyclopedia of conditions and indications in every anatomic region, as well as numerous case studies. – Techniques of neural therapy – a comprehensive, substantially illustrated list of injection procedures, including detailed guidance on insertion points, direction, and depth. Distilling decades of clinical research and hands-on experience, this unique book is essential reading for practitioners of all disciplines interested in exploring how contemporary neural therapy can complement and enhance the way they practice medicine.

/ / похожие

Подробнее#### Nan Zheng Learning in Energy-Efficient Neuromorphic Computing: Algorithm and Architecture Co-Design

Explains current co-design and co-optimization methodologies for building hardware neural networks and algorithms for machine learning applications This book focuses on how to build energy-efficient hardware for neural networks with learning capabilities—and provides co-design and co-optimization methodologies for building hardware neural networks that can learn. Presenting a complete picture from high-level algorithm to low-level implementation details, Learning in Energy-Efficient Neuromorphic Computing: Algorithm and Architecture Co-Design also covers many fundamentals and essentials in neural networks (e. g. , deep learning), as well as hardware implementation of neural networks. The book begins with an overview of neural networks. It then discusses algorithms for utilizing and training rate-based artificial neural networks. Next comes an introduction to various options for executing neural networks, ranging from general-purpose processors to specialized hardware, from digital accelerator to analog accelerator. A design example on building energy-efficient accelerator for adaptive dynamic programming with neural networks is also presented. An examination of fundamental concepts and popular learning algorithms for spiking neural networks follows that, along with a look at the hardware for spiking neural networks. Then comes a chapter offering readers three design examples (two of which are based on conventional CMOS, and one on emerging nanotechnology) to implement the learning algorithm found in the previous chapter. The book concludes with an outlook on the future of neural network hardware. Includes cross-layer survey of hardware accelerators for neuromorphic algorithms Covers the co-design of architecture and algorithms with emerging devices for much-improved computing efficiency Focuses on the co-design of algorithms and hardware, which is especially critical for using emerging devices, such as traditional memristors or diffusive memristors, for neuromorphic computing Learning in Energy-Efficient Neuromorphic Computing: Algorithm and Architecture Co-Design is an ideal resource for researchers, scientists, software engineers, and hardware engineers dealing with the ever-increasing requirement on power consumption and response time. It is also excellent for teaching and training undergraduate and graduate students about the latest generation neural networks with powerful learning capabilities.

/ / похожие

Подробнее#### Antonios K. Alexandridis Wavelet Neural Networks

A step-by-step introduction to modeling, training, and forecasting using wavelet networks Wavelet Neural Networks: With Applications in Financial Engineering, Chaos, and Classification presents the statistical model identification framework that is needed to successfully apply wavelet networks as well as extensive comparisons of alternate methods. Providing a concise and rigorous treatment for constructing optimal wavelet networks, the book links mathematical aspects of wavelet network construction to statistical modeling and forecasting applications in areas such as finance, chaos, and classification. The authors ensure that readers obtain a complete understanding of model identification by providing in-depth coverage of both model selection and variable significance testing. Featuring an accessible approach with introductory coverage of the basic principles of wavelet analysis, Wavelet Neural Networks: With Applications in Financial Engineering, Chaos, and Classification also includes: • Methods that can be easily implemented or adapted by researchers, academics, and professionals in identification and modeling for complex nonlinear systems and artificial intelligence • Multiple examples and thoroughly explained procedures with numerous applications ranging from financial modeling and financial engineering, time series prediction and construction of confidence and prediction intervals, and classification and chaotic time series prediction • An extensive introduction to neural networks that begins with regression models and builds to more complex frameworks • Coverage of both the variable selection algorithm and the model selection algorithm for wavelet networks in addition to methods for constructing confidence and prediction intervals Ideal as a textbook for MBA and graduate-level courses in applied neural network modeling, artificial intelligence, advanced data analysis, time series, and forecasting in financial engineering, the book is also useful as a supplement for courses in informatics, identification and modeling for complex nonlinear systems, and computational finance. In addition, the book serves as a valuable reference for researchers and practitioners in the fields of mathematical modeling, engineering, artificial intelligence, decision science, neural networks, and finance and economics.

/ / похожие

Подробнее