Download or read book Adaptive Optimal control Algorithms for Brainlike Networks written by and published by . This book was released on 2006 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: Many neural control systems are at least roughly optimized, but how is optimal control learned in the brain? There are algorithms for this purpose, but in their present forms they aren't suited for biological neural networks because they rely on a type of communication that isn't available in the brain, namely weight transport -- transmitting the strengths, or "weights", of individual synapses to other synapses and neurons. Here I show how optimal control can be learned without weight transport. I explore three complementary approaches. In the first, I show that the control-theory concept of feedback linearization can form the basis for a simple mechanism that learns roughly optimal control, at least in some sensorimotor tasks. Second, I describe a method based on Pontryagin's Minimum Principle of optimal control, by which a network without weight transport might achieve optimal open-loop control. Third, I describe a mechanism for building optimal feedback controllers, without weight transport, by a method based on generalized Hamilton-Jacobi-Bellman equations. Finally, I argue that the issues raised in these three projects apply quite broadly, i.e. most control algorithms rely on weight transport in many different ways, but it may be possible to recast them into forms that are free of such transport by the mechanisms I propose.
Download or read book Adaptive Optimal control Algorithms for Brainlike Networks written by Lakshminarayan Chinta Venkateswararao and published by . This book was released on 2010 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: Many neural control systems are at least roughly optimized, but how is optimal control learned in the brain? There are algorithms for this purpose, but in their present forms they aren't suited for biological neural networks because they rely on a type of communication that isn't available in the brain, namely weight transport - transmitting the strengths, or "weights", of individual synapses to other synapses and neurons. Here I show how optimal control can be learned without weight transport. I explore three complementary approaches. In the first, I show that the control-theory concept of feedback linearization can form the basis for a simple mechanism that learns roughly optimal control, at least in some sensorimotor tasks. Second, I describe a method based on Pontryagin's Minimum Principle of optimal control, by which a network without weight transport might achieve optimal open-loop control. Third, I describe a mechanism for building optimal feedback controllers, without weight transport, by a method based on generalized Hamilton-Jacobi-Bellman equations. Finally, I argue that the issues raised in these three projects apply quite broadly, i.e. most control algorithms rely on weight transport in many different ways, but it may be possible to recast them into forms that are free of such transport by the mechanisms I propose.
Download or read book Adaptive Dynamic Programming for Control written by Huaguang Zhang and published by Springer. This book was released on 2015-01-28 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: There are many methods of stable controller design for nonlinear systems. In seeking to go beyond the minimum requirement of stability, Adaptive Dynamic Programming in Discrete Time approaches the challenging topic of optimal control for nonlinear systems using the tools of adaptive dynamic programming (ADP). The range of systems treated is extensive; affine, switched, singularly perturbed and time-delay nonlinear systems are discussed as are the uses of neural networks and techniques of value and policy iteration. The text features three main aspects of ADP in which the methods proposed for stabilization and for tracking and games benefit from the incorporation of optimal control methods: • infinite-horizon control for which the difficulty of solving partial differential Hamilton–Jacobi–Bellman equations directly is overcome, and proof provided that the iterative value function updating sequence converges to the infimum of all the value functions obtained by admissible control law sequences; • finite-horizon control, implemented in discrete-time nonlinear systems showing the reader how to obtain suboptimal control solutions within a fixed number of control steps and with results more easily applied in real systems than those usually gained from infinite-horizon control; • nonlinear games for which a pair of mixed optimal policies are derived for solving games both when the saddle point does not exist, and, when it does, avoiding the existence conditions of the saddle point. Non-zero-sum games are studied in the context of a single network scheme in which policies are obtained guaranteeing system stability and minimizing the individual performance function yielding a Nash equilibrium. In order to make the coverage suitable for the student as well as for the expert reader, Adaptive Dynamic Programming in Discrete Time: • establishes the fundamental theory involved clearly with each chapter devoted to a clearly identifiable control paradigm; • demonstrates convergence proofs of the ADP algorithms to deepen understanding of the derivation of stability and convergence with the iterative computational methods used; and • shows how ADP methods can be put to use both in simulation and in real applications. This text will be of considerable interest to researchers interested in optimal control and its applications in operations research, applied mathematics computational intelligence and engineering. Graduate students working in control and operations research will also find the ideas presented here to be a source of powerful methods for furthering their study.
Download or read book Adaptive Dynamic Programming with Applications in Optimal Control written by Derong Liu and published by Springer. This book was released on 2017-01-04 with total page 609 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book covers the most recent developments in adaptive dynamic programming (ADP). The text begins with a thorough background review of ADP making sure that readers are sufficiently familiar with the fundamentals. In the core of the book, the authors address first discrete- and then continuous-time systems. Coverage of discrete-time systems starts with a more general form of value iteration to demonstrate its convergence, optimality, and stability with complete and thorough theoretical analysis. A more realistic form of value iteration is studied where value function approximations are assumed to have finite errors. Adaptive Dynamic Programming also details another avenue of the ADP approach: policy iteration. Both basic and generalized forms of policy-iteration-based ADP are studied with complete and thorough theoretical analysis in terms of convergence, optimality, stability, and error bounds. Among continuous-time systems, the control of affine and nonaffine nonlinear systems is studied using the ADP approach which is then extended to other branches of control theory including decentralized control, robust and guaranteed cost control, and game theory. In the last part of the book the real-world significance of ADP theory is presented, focusing on three application examples developed from the authors’ work: • renewable energy scheduling for smart power grids;• coal gasification processes; and• water–gas shift reactions. Researchers studying intelligent control methods and practitioners looking to apply them in the chemical-process and power-supply industries will find much to interest them in this thorough treatment of an advanced approach to control.
Download or read book Handbook of Intelligent Control written by David A. White and published by Van Nostrand Reinhold Company. This book was released on 1992 with total page 600 pages. Available in PDF, EPUB and Kindle. Book excerpt: This handbook shows the reader how to develop neural networks and apply them to various engineering control problems. Based on a workshop on aerospace applications, this tutorial covers integration of neural networks with existing control architectures as well as new neurocontrol architectures in nonlinear control.
Download or read book Adaptive Control with Recurrent High order Neural Networks written by George A. Rovithakis and published by Springer Science & Business Media. This book was released on 2012-12-06 with total page 203 pages. Available in PDF, EPUB and Kindle. Book excerpt: The series Advances in Industrial Control aims to report and encourage technology transfer in control engineering. The rapid development of control technology has an impact on all areas of the control discipline. New theory, new controllers, actuators, sensors, new industrial processes, computer methods, new applications, new philosophies ... , new challenges. Much of this development work resides in industrial reports, feasibility study papers and the reports of advanced collaborative projects. The series offers an opportunity for researchers to present an extended exposition of such new work in all aspects of industrial control for wider and rapid dissemination. Neural networks is one of those areas where an initial burst of enthusiasm and optimism leads to an explosion of papers in the journals and many presentations at conferences but it is only in the last decade that significant theoretical work on stability, convergence and robustness for the use of neural networks in control systems has been tackled. George Rovithakis and Manolis Christodoulou have been interested in these theoretical problems and in the practical aspects of neural network applications to industrial problems. This very welcome addition to the Advances in Industrial Control series provides a succinct report of their research. The neural network model at the core of their work is the Recurrent High Order Neural Network (RHONN) and a complete theoretical and simulation development is presented. Different readers will find different aspects of the development of interest. The last chapter of the monograph discusses the problem of manufacturing or production process scheduling.
Download or read book Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles written by Draguna L. Vrabie and published by IET. This book was released on 2013 with total page 305 pages. Available in PDF, EPUB and Kindle. Book excerpt: The book reviews developments in the following fields: optimal adaptive control; online differential games; reinforcement learning principles; and dynamic feedback control systems.
Download or read book Discrete time Control Algorithms and Adaptive Intelligent Systems Designs written by Asma Azmi Al-Tamimi and published by ProQuest. This book was released on 2007 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: In this work, approximate dynamic programming (ADP) designs based on adaptive critic structures are developed to solve the discrete-time H2/Hinfinity optimal control problems in which the state and action spaces are continuous. This work considers linear discrete-time systems as well as nonlinear discrete-time systems that are affine in the input. This research resulted in forward-in-time reinforcement learning algorithms that converge to the solution of the Generalized Algebraic Riccati Equation (GARE) for linear systems. For the nonlinear case, a forward-in-time reinforcement learning algorithm is presented that converges to the solution of the associated Hamilton-Jacobi Bellman equation (HJB). The results in the linear case can be thought of as a way to solve the GARE of the well-known discrete-time Hinfinity optimal control problem forward in time. Four design algorithms are developed: Heuristic Dynamic programming (HDP), Dual Heuristic dynamic programming (DHP), Action dependent Heuristic Dynamic programming (ADHDP) and Action dependent Dual Heuristic dynamic programming (ADDHP). The significance of these algorithms is that for some of them, particularly the ADHDP algorithm, a priori knowledge of the plant model is not required to solve the dynamic programming problem. Another major outcome of this work is that we introduce a convergent policy iteration scheme based on the HDP algorithm that allows the use of neural networks to arbitrarily approximate for the value function of the discrete-time HJB equation. This online algorithm may be implemented in a way that requires only partial knowledge of the model of the nonlinear dynamical system. The dissertation includes detailed proofs of convergence for the proposed algorithms, HDP, DHP, ADHDP, ADDHP and the nonlinear HDP. Practical numerical examples are provided to show the effectiveness of the developed optimization algorithms. For nonlinear systems, a comparison with methods based on the State-Dependent Riccati Equation (SDRE) is also presented. In all the provided examples, parametric structures like neural networks have been used to find compact representations of the value function and optimal policies for the corresponding optimal control problems.
Download or read book Optimal Control of Impulsive Systems Using Adaptive Critic Based Neural Networks written by Xiaohua Wang and published by . This book was released on 2008 with total page 240 pages. Available in PDF, EPUB and Kindle. Book excerpt: "This dissertation presents systematic computational tools for the optimal control synthesis of fixed-time and variable-time impulsive systems. Necessary conditions for optimality have been derived for a fixed-time and a variable-time impulsive system using the calculus of variations method. Properties of the costates and the states relation are studied and presented in theorems for the optimal control of a linear fixed-time impulsive system. Optimal control of a variable-time impulsive problem is investigated. A single neural network adaptive critic (SNAC) method for an impulsive system is developed. Algorithms are presented for calculating the optimal impulsive solutions in finite and infinite horizon cases. Since the construction of the networks and the synthesis of the controllers are relatively free of problem-specific assumptions, the method presented here is suitable for a wide range of real life nonlinear impulsive systems. Linear and nonlinear examples of impulsive systems with continuous and impulsive dynamics are considered for the proposed method and algorithms. The given examples show that the proposed method provides the optimal solution for finite and infinite horizon cases"--Abstract, leaf iii.
Download or read book Time optimal Control with Adaptive Networks written by James Wesley Berkovec and published by . This book was released on 1964 with total page 160 pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Direct Adaptive Control Algorithms written by Howard Kaufman and published by Springer Science & Business Media. This book was released on 2012-12-06 with total page 380 pages. Available in PDF, EPUB and Kindle. Book excerpt: Suitable either as a reference or as a text for a graduate course in adaptive control systems, this book is a self-contained compendium of easily implementable adaptive control algorithms that have been developed and applied by the authors for over 10 years. These algorithms do not require explicit process parameter identification and have been successfully applied to a wide variety of engineering problems including flexible structure control, blood pressure control and robotics. In general, these algorithms are suitable for a wide class of multiple input-output control systems containing significant uncertainty as well as disturbances.
Download or read book Applications of Neural Adaptive Control Technology written by Jens Kalkkuhl and published by World Scientific. This book was released on 1997 with total page 328 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book presents the results of the second workshop on Neural Adaptive Control Technology, NACT II, held on September 9-10, 1996, in Berlin. The workshop was organised in connection with a three-year European-Union-funded Basic Research Project in the ESPRIT framework, called NACT, a collaboration between Daimler-Benz (Germany) and the University of Glasgow (Scotland).The NACT project, which began on 1 April 1994, is a study of the fundamental properties of neural-network-based adaptive control systems. Where possible, links with traditional adaptive control systems are exploited. A major aim is to develop a systematic engineering procedure for designing neural controllers for nonlinear dynamic systems. The techniques developed are being evaluated on concrete industrial problems from within the Daimler-Benz group of companies.The aim of the workshop was to bring together selected invited specialists in the fields of adaptive control, nonlinear systems and neural networks. The first workshop (NACT I) took place in Glasgow in May 1995 and was mainly devoted to theoretical issues of neural adaptive control. Besides monitoring further development of theory, the NACT II workshop was focused on industrial applications and software tools. This context dictated the focus of the book and guided the editors in the choice of the papers and their subsequent reshaping into substantive book chapters. Thus, with the project having progressed into its applications stage, emphasis is put on the transfer of theory of neural adaptive engineering into industrial practice. The contributors are therefore both renowned academics and practitioners from major industrial users of neurocontrol.
Download or read book Adaptive Critic Control with Robust Stabilization for Uncertain Nonlinear Systems written by Ding Wang and published by Springer. This book was released on 2018-08-10 with total page 317 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book reports on the latest advances in adaptive critic control with robust stabilization for uncertain nonlinear systems. Covering the core theory, novel methods, and a number of typical industrial applications related to the robust adaptive critic control field, it develops a comprehensive framework of robust adaptive strategies, including theoretical analysis, algorithm design, simulation verification, and experimental results. As such, it is of interest to university researchers, graduate students, and engineers in the fields of automation, computer science, and electrical engineering wishing to learn about the fundamental principles, methods, algorithms, and applications in the field of robust adaptive critic control. In addition, it promotes the development of robust adaptive critic control approaches, and the construction of higher-level intelligent systems.
Download or read book Evolutionary Learning Algorithms for Neural Adaptive Control written by Dimitris C. Dracopoulos and published by Springer. This book was released on 1997-08-15 with total page 236 pages. Available in PDF, EPUB and Kindle. Book excerpt: After an introduction to neural networks and genetic algorithms, this volume describes in detail how neural networks and evolutionary techniques (specifically genetic algorithms and genetic programming) can be applied to the adaptive control of complex dynamic systems (including chaotic ones). A number of examples are presented and useful tips are given for the application of the techniques described. The fundamentals of dynamic systems theory and classical adaptive control are also given. This volume will be of particular interest to undergraduate and postgraduate students taking courses in neural networks, genetic algorithms or control systems, researchers in neural networks and genetic algorithms who need to extend their field of application to dynamic systems and control, and control theorists/professionals who would like to use these advanced learning techniques for solving high-nonlinear control theory problems.
Download or read book High Level Feedback Control with Neural Networks written by Young Ho Kim and published by World Scientific. This book was released on 1998 with total page 232 pages. Available in PDF, EPUB and Kindle. Book excerpt: Complex industrial or robotic systems with uncertainty and disturbances are difficult to control. As system uncertainty or performance requirements increase, it becomes necessary to augment traditional feedback controllers with additional feedback loops that effectively "add intelligence" to the system. Some theories of artificial intelligence (AI) are now showing how complex machine systems should mimic human cognitive and biological processes to improve their capabilities for dealing with uncertainty. This book bridges the gap between feedback control and AI. It provides design techniques for "high-level" neural-network feedback-control topologies that contain servo-level feedback-control loops as well as AI decision and training at the higher levels. Several advanced feedback topologies containing neural networks are presented, including "dynamic output feedback", "reinforcement learning" and "optimal design", as well as a "fuzzy-logic reinforcement" controller. The control topologies areintuitive, yet are derived using sound mathematical principles where proofs of stability are given so that closed-loop performance can be relied upon in using these control systems. Computer-simulation examples are given to illustrate the performance.
Download or read book Closing the Loop written by Julia Santos and published by . This book was released on 2015 with total page 57 pages. Available in PDF, EPUB and Kindle. Book excerpt: The Caenorhabditis elegans (C. elegans) worm is a well-studied biological organism model. The nervous system of C. elegans is particularly appealing to study, since it is a tractable fully functional neuronal network for which electro-physical connectivity map (connectome) is fully resolved [1,2]. In this work, we use a recently established computational dynamical model of the C. elegans nervous system, which incorporated the static connectome data with intrinsic properties of neurons and their interactions. With this model, it has been demonstrated that robust oscillatory movements in motor neurons along the body can be invoked by constant current excitation of command sensory neurons (e.g., PLM neurons associated with forward crawling), and that their activation corresponds to low-dimensional Hopf bifurcation [3]. While these first results validated the model, it is exciting to learn and visualize how the nervous system transforms its oscillatory dynamics to the muscles to support robust full body movements (e.g., forward crawling) [4]. Moreover, it is intriguing to understand the optimal sensory stimulations that cause these movements to persist. We explore these questions by developing methods to visualize network activity in a physical space and creating a model for C. elegans musculature as a viscoelastic rod with discrete rigid segments [5]. We map the neuronal dynamics such that they activate the muscles and deform the rod. When motor neuron activity stimulates muscles [2], this activation is translated into force applied to the rod, which moves in accordance with the physical properties of C. elegans. By stimulating the command PLM neurons, we establish for the first time that motor neuron dynamics are indeed producing coherent oscillatory full body movements that resemble forward crawling. We utilize our computational full body model to determine the appropriate sensory input for behavior, such as crawling, to persist after explicit external stimulation (touch) has ceased, as observed in experiments [5]. Since such persistence could be explained by a feedback loop between the environment and sensory neurons, we propose an adaptive control algorithm that extends existing recursive least squares-based algorithms (e.g., FORCE [6]). The RLS algorithm is divided into training and operational phases. In the training phase, we reduce the error between desired and actual outputs by making small, rapid modifications to the weights which are applied to the network input (feedback). When the weighted feedback into sensory neurons prompts the system to produce the desired output without significant weight modification between iterations, a correct set of weights has been found [6]. We use a low-dimensional projection of motor neuron dynamics to calculate expected and actual output, and our algorithm is capable of finding sensory input patterns that will lead to the desired movement.
Download or read book Advances in Neural Networks ISNN 2017 written by Fengyu Cong and published by Springer. This book was released on 2017-06-14 with total page 614 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book constitutes the refereed proceedings of the 14th International Symposium on Neural Networks, ISNN 2017, held in Sapporo, Hakodate, and Muroran, Hokkaido, Japan, in June 2017. The 135 revised full papers presented in this two-volume set were carefully reviewed and selected from 259 submissions. The papers cover topics like perception, emotion and development, action and motor control, attractor and associative memory, neurodynamics, complex systems, and chaos.
