Yunong Zhang – författare

Toward Deep Neural Networks: WASD Neuronet Models, Algorithms, and Applications introduces the outlook and extension toward deep neural networks, with a focus on the weights-and-structure determination (WASD) algorithm. Based on the authors’ 20 years of research experience on neuronets, the book explores the models, algorithms, and applications of the WASD neuronet, and allows reader to extend the techniques in the book to solve scientific and engineering problems. The book will be of interest to engineers, senior undergraduates, postgraduates, and researchers in the fields of neuronets, computer mathematics, computer science, artificial intelligence, numerical algorithms, optimization, simulation and modeling, deep learning, and data mining. Features Focuses on neuronet models, algorithms, and applications Designs, constructs, develops, analyzes, simulates and compares various WASD neuronet models, such as single-input WASD neuronet models, two-input WASD neuronet models, three-input WASD neuronet models, and general multi-input WASD neuronet models for function data approximations Includes real-world applications, such as population prediction Provides complete mathematical foundations, such as Weierstrass approximation, Bernstein polynomial approximation, Taylor polynomial approximation, and multivariate function approximation, exploring the close integration of mathematics (i.e., function approximation theories) and computers (e.g., computer algorithms) Utilizes the authors' 20 years of research on neuronets

This book aims to solve the discrete implementation problems of continuous-time neural network models while improving the performance of neural networks by using various Zhang Time Discretization (ZTD) formulas.The authors summarize and present the systematic derivations and complete research of ZTD formulas from special 3S-ZTD formulas to general NS-ZTD formulas. These finally lead to their proposed discrete-time Zhang neural network (DTZNN) algorithms, which are more efficient, accurate, and elegant. This book will open the door to scientific and engineering applications of ZTD formulas and neural networks, and will be a major inspiration for studies in neural network modeling, numerical algorithm design, prediction, and robot manipulator control.The book will benefit engineers, senior undergraduates, graduate students, and researchers in the fields of neural networks, computer mathematics, computer science, artificial intelligence, numerical algorithms, optimization, robotics, and simulation modeling.

This book aims to solve the discrete implementation problems of continuous-time neural network models while improving the performance of neural networks by using various Zhang Time Discretization (ZTD) formulas.The authors summarize and present the systematic derivations and complete research of ZTD formulas from special 3S-ZTD formulas to general NS-ZTD formulas. These finally lead to their proposed discrete-time Zhang neural network (DTZNN) algorithms, which are more efficient, accurate, and elegant. This book will open the door to scientific and engineering applications of ZTD formulas and neural networks, and will be a major inspiration for studies in neural network modeling, numerical algorithm design, prediction, and robot manipulator control.The book will benefit engineers, senior undergraduates, graduate students, and researchers in the fields of neural networks, computer mathematics, computer science, artificial intelligence, numerical algorithms, optimization, robotics, and simulation modeling.

The latest in parallel EM solutions with both in-core and out-of-core solversThe solution of complex electromagnetic (EM) problems requires one to address the issues related with numerical accuracy and efficient distribution of the solution procedure over multiple computational nodes. With the advent of multicore processors and high performance computing (HPC) technology, the EM software designers need to know how to add new functionality to computational EM codes so that they can run efficiently on these new processors.Higher Order Basis Based Integral Equation Solver [HOBBIES] presents a road map for the analysis of complex material structures using the high-performance parallel simulation software known as HOBBIES. Focusing on the Method of Moments (MoM), the book features new parallel programming techniques and user-friendly code with superior capabilities for solving challenging EM radiation and scattering problems. It provides readers with complete guidance on how to extend the capability of MoM and achieve faster and more accurate EM analysis and utilize multicore CPUs on desktop computers. Complete with an academic version of the HOBBIES software, this book: Explains the unique features of the higher order basis functions in the solution of integral equations in a MoM contextShows how to generate a properly load balanced parallel computational procedure for MoM matrix filling and matrix equation solving in both in-core and out-of-core implementationPresents a professional graphical users interface (GUI) for generating the geometrical structure based on NURBS modelingIllustrates various automatic meshing procedures based on an a-priori defined error between the actual geometry and the meshed structureOutlines all the key features of the HOBBIES software, including multiple optimization procedures for EM synthesisThe bottleneck of traditional MoM arises from the lack of memory in computers for solution of large problems. This is mitigated by using higher order basis functions and out-of-core solver in HOBBIES. HOBBIES has the capability to perform numerically accurate EM simulations using thousands of CPU cores in an HPC environment using a properly load balanced out-of-core solver. In this way, it provides a cost-effective choice for addressing modern engineering and scientific challenges that arise from the extremely complicated real-life applications.

Introduces a revolutionary, quadratic-programming based approach to solving long-standing problems in motion planning and control of redundant manipulators This book describes a novel quadratic programming approach to solving redundancy resolutions problems with redundant manipulators. Known as ``QP-unified motion planning and control of redundant manipulators'' theory, it systematically solves difficult optimization problems of inequality-constrained motion planning and control of redundant manipulators that have plagued robotics engineers and systems designers for more than a quarter century.    An example of redundancy resolution could involve a robotic limb with six joints, or degrees of freedom (DOFs), with which to position an object. As only five numbers are required to specify the position and orientation of the object, the robot can move with one remaining DOF through practically infinite poses while performing a specified task. In this case redundancy resolution refers to the process of choosing an optimal pose from among that infinite set. A critical issue in robotic systems control, the redundancy resolution problem has been widely studied for decades, and numerous solutions have been proposed. This book investigates various approaches to motion planning and control of redundant robot manipulators and describes the most successful strategy thus far developed for resolving redundancy resolution problems.  Provides a fully connected, systematic, methodological, consecutive, and easy approach to solving redundancy resolution problemsDescribes a new approach to the time-varying Jacobian matrix pseudoinversion, applied to the redundant-manipulator kinematic controlIntroduces The QP-based unification of robots' redundancy resolutionIllustrates the effectiveness of the methods presented using a large number of computer simulation results based on PUMA560, PA10, and planar robot manipulatorsProvides technical details for all schemes and solvers presented, for readers to adopt and customize them for specific industrial applications Robot Manipulator Redundancy Resolution is must-reading for advanced undergraduates and graduate students of robotics, mechatronics, mechanical engineering, tracking control, neural dynamics/neural networks, numerical algorithms, computation and optimization, simulation and modelling, analog, and digital circuits. It is also a valuable working resource for practicing robotics engineers and systems designers and industrial researchers.

Toward Deep Neural Networks: WASD Neuronet Models, Algorithms, and Applications introduces the outlook and extension toward deep neural networks, with a focus on the weights-and-structure determination (WASD) algorithm. Based on the authors’ 20 years of research experience on neuronets, the book explores the models, algorithms, and applications of the WASD neuronet, and allows reader to extend the techniques in the book to solve scientific and engineering problems. The book will be of interest to engineers, senior undergraduates, postgraduates, and researchers in the fields of neuronets, computer mathematics, computer science, artificial intelligence, numerical algorithms, optimization, simulation and modeling, deep learning, and data mining. Features Focuses on neuronet models, algorithms, and applications Designs, constructs, develops, analyzes, simulates and compares various WASD neuronet models, such as single-input WASD neuronet models, two-input WASD neuronet models, three-input WASD neuronet models, and general multi-input WASD neuronet models for function data approximations Includes real-world applications, such as population prediction Provides complete mathematical foundations, such as Weierstrass approximation, Bernstein polynomial approximation, Taylor polynomial approximation, and multivariate function approximation, exploring the close integration of mathematics (i.e., function approximation theories) and computers (e.g., computer algorithms) Utilizes the authors' 20 years of research on neuronets

Neural networks and neural dynamics are powerful approaches for the online solution of mathematical problems arising in many areas of science, engineering, and business. Compared with conventional gradient neural networks that only deal with static problems of constant coefficient matrices and vectors, the authors’ new method called zeroing dynamics solves time-varying problems. Zeroing Dynamics, Gradient Dynamics, and Newton Iterations is the first book that shows how to accurately and efficiently solve time-varying problems in real-time or online using continuous- or discrete-time zeroing dynamics. The book brings together research in the developing fields of neural networks, neural dynamics, computer mathematics, numerical algorithms, time-varying computation and optimization, simulation and modeling, analog and digital hardware, and fractals.The authors provide a comprehensive treatment of the theory of both static and dynamic neural networks. Readers will discover how novel theoretical results have been successfully applied to many practical problems. The authors develop, analyze, model, simulate, and compare zeroing dynamics models for the online solution of numerous time-varying problems, such as root finding, nonlinear equation solving, matrix inversion, matrix square root finding, quadratic optimization, and inequality solving.

Exploration on how neurodynamic methods can be effectively applied to control complex, flexible robotic systems in research, and real-world settings Neurodynamic Methods for Continuum Robot Control presents a comprehensive exploration of neurodynamic control methods for continuum robots—a new generation of soft, flexible robotic systems inspired by nature. The book is organized into seven thematic parts and eleven chapters, progressing from fundamental analytical techniques to advanced hybrid and adaptive control systems. After the introduction chapter, each chapter includes detailed theoretical derivations, algorithm design, and extensive validation through simulations and physical experiments. This book explores how continuum robots are controlled effectively and robustly in real time, without requiring complex modeling or extensive data training. The solution explored throughout this book is a suite of neurodynamic control algorithms, which offer a powerful alternative to traditional model-based and learning-based approaches. These neurodynamic methods—particularly gradient neurodynamics (GND) and zeroing neurodynamics (ZND)—allow for fast, adaptive, and model-free solutions to inverse kinematics and trajectory tracking problems. Written by a team of highly qualified authors with extensive experience in the field, this book includes information on: Inherent challenges in modeling and controlling continuum robots, including model uncertainty, high dimensionality, and elastic deformationMathematical foundations of GND and ZND and the derivation and application of Jacobian-based and model-free kinematic control methodsAdvanced neurodynamic models including predefined-time convergent, time-synchronized, and varying-parameter schemesHybrid intelligent methods such as fuzzy logic-enhanced neurodynamics and cerebellum-inspired architecturesBenefits of neurodynamic control, including real-time performance, robustness, adaptability, and simplicity in deploymentDiscussing theory, design, and applications to deliver state-of-the-art research, Neurodynamic Methods for Continuum Robot Control is an essential resource on the subject for researchers, graduate students, and advanced practitioners—not only a technical reference, but also a visionary guide to the future of intelligent robotics.

Neural networks and neural dynamics are powerful approaches for the online solution of mathematical problems arising in many areas of science, engineering, and business. Compared with conventional gradient neural networks that only deal with static problems of constant coefficient matrices and vectors, the authors’ new method called zeroing dynamics solves time-varying problems. Zeroing Dynamics, Gradient Dynamics, and Newton Iterations is the first book that shows how to accurately and efficiently solve time-varying problems in real-time or online using continuous- or discrete-time zeroing dynamics. The book brings together research in the developing fields of neural networks, neural dynamics, computer mathematics, numerical algorithms, time-varying computation and optimization, simulation and modeling, analog and digital hardware, and fractals.The authors provide a comprehensive treatment of the theory of both static and dynamic neural networks. Readers will discover how novel theoretical results have been successfully applied to many practical problems. The authors develop, analyze, model, simulate, and compare zeroing dynamics models for the online solution of numerous time-varying problems, such as root finding, nonlinear equation solving, matrix inversion, matrix square root finding, quadratic optimization, and inequality solving.

The volume LNCS 9377 constitutes the refereed proceedings of the 12th International Symposium on Neural Networks, ISNN 2015, held in Jeju, South Korea in October 2015.

Repetitive Motion Planning and Control of Redundant Robot Manipulators presents four typical motion planning schemes based on optimization techniques, including the fundamental RMP scheme and its extensions. These schemes are unified as quadratic programs (QPs), which are solved by neural networks or numerical algorithms. The RMP schemes are demonstrated effectively by the simulation results based on various robotic models; the experiments applying the fundamental RMP scheme to a physical robot manipulator are also presented. As the schemes and the corresponding solvers presented in the book have solved the non-repetitive motion problems existing in redundant robot manipulators, it is of particular use in applying theoretical research based on the quadratic program for redundant robot manipulators in industrial situations. This book will be a valuable reference work for engineers, researchers, advanced undergraduate and graduate students in robotics fields.Yunong Zhang is a professor at The School of Information Science and Technology, Sun Yat-sen University, Guangzhou, China; Zhijun Zhang is a research fellow working at the same institute.

Repetitive Motion Planning and Control of Redundant Robot Manipulators presents four typical motion planning schemes based on optimization techniques, including the fundamental RMP scheme and its extensions. These schemes are unified as quadratic programs (QPs), which are solved by neural networks or numerical algorithms. The RMP schemes are demonstrated effectively by the simulation results based on various robotic models; the experiments applying the fundamental RMP scheme to a physical robot manipulator are also presented. As the schemes and the corresponding solvers presented in the book have solved the non-repetitive motion problems existing in redundant robot manipulators, it is of particular use in applying theoretical research based on the quadratic program for redundant robot manipulators in industrial situations. This book will be a valuable reference work for engineers, researchers, advanced undergraduate and graduate students in robotics fields.Yunong Zhang is a professor at The School of Information Science and Technology, Sun Yat-sen University, Guangzhou, China; Zhijun Zhang is a research fellow working at the same institute.

This book focuses on solving different types of time-varying problems. It presents various Zhang dynamics (ZD) models by defining various Zhang functions (ZFs) in real and complex domains. It then provides theoretical analyses of such ZD models and illustrates their results. It also uses simulations to substantiate their efficacy and show the feasibility of the presented ZD approach (i.e., different ZFs leading to different ZD models), which is further applied to the repetitive motion planning (RMP) of redundant robots, showing its application potential.

This book focuses on solving different types of time-varying problems. It presents various Zhang dynamics (ZD) models by defining various Zhang functions (ZFs) in real and complex domains. It then provides theoretical analyses of such ZD models and illustrates their results. It also uses simulations to substantiate their efficacy and show the feasibility of the presented ZD approach (i.e., different ZFs leading to different ZD models), which is further applied to the repetitive motion planning (RMP) of redundant robots, showing its application potential.

This book introduces readers to using the simple but effective Zhang-gradient (ZG) method to solve tracking-control problems concerning various nonlinear systems, while also highlighting the applications of the ZG method to tracking control for practical systems, e.g.