Architecture Solutions for E-Learning Systems


Book Description

"This book provides fundamental research on the architecture of learning technology systems, discussing such issues as the common structures in LTS and solutions for specific forms such as knowledge-based, distributed, or adaptive applications of e-learning. Researchers, and scholars in the fields of learning content software development, computing and educational technologies, and e-learning will find it an invaluable resource"--Provided by publisher.




Decentralized Control of Large-Scale Systems


Book Description

A large-scale system is composed of several interconnected subsystems. For such a system it is often desired to have some form of decentralization in the control structure, since it is typically not realistic to assume that all output measurements can be transmitted to every local control station. Problems of this kind can appear in electric power systems, communication networks, large space structures, robotic systems, economic systems, and traffic networks, to name only a few. Typical large-scale control systems have several local control stations which observe only local outputs and control only local inputs. All controllers are involved, however, in the control operation of the overall system. The focus of this book is on the efficient control of interconnected systems, and it presents systems analysis and controller synthesis techniques using a variety of methods. A systematic study of multi-input, multi-output systems is carried out and illustrative examples are given to clarify the ideas.




Autonomic and Trusted Computing


Book Description

This book constitutes the refereed procedings of the 6th International Conference on Autonomic and Trusted Computing, ATC 2009, held in Brisbane, Australia, in July 2009, co-located with UIC 2009, the 6th International Conference on Ubiquitous Intelligence and Computing. The 17 revised full papers presented together with one invited paper and one keynote talk were carefully reviewed and selected from 52 submissions. The regular papers are organized in topical sections on organic and autonomic computing, trusted computing, wireless sensor networks, and trust.




Decentralised Reinforcement Learning in Markov Games


Book Description

Introducing a new approach to multiagent reinforcement learning and distributed artificial intelligence, this guide shows how classical game theory can be used to compose basic learning units. This approach to creating agents has the advantage of leading to powerful, yet intuitively simple, algorithms that can be analyzed. The setup is demonstrated here in a number of different settings, with a detailed analysis of agent learning behaviors provided for each. A review of required background materials from game theory and reinforcement learning is also provided, along with an overview of related multiagent learning methods.




Optimization Algorithms for Distributed Machine Learning


Book Description

This book discusses state-of-the-art stochastic optimization algorithms for distributed machine learning and analyzes their convergence speed. The book first introduces stochastic gradient descent (SGD) and its distributed version, synchronous SGD, where the task of computing gradients is divided across several worker nodes. The author discusses several algorithms that improve the scalability and communication efficiency of synchronous SGD, such as asynchronous SGD, local-update SGD, quantized and sparsified SGD, and decentralized SGD. For each of these algorithms, the book analyzes its error versus iterations convergence, and the runtime spent per iteration. The author shows that each of these strategies to reduce communication or synchronization delays encounters a fundamental trade-off between error and runtime.




Iterative Learning Control for Nonlinear Time-Delay System


Book Description

This book focuses on adaptive iterative learning control problem for nonlinear time-delay systems.A universal adaptive learning control scheme is provided for a wide classes of nonlinear systems with time-varying delay and input nonlinearity. Proceeding from easy to difficult, this book deals with the adaptive iterative learning control problems for parameterized nonlinear time-delay systems, non-parameterized nonlinear time-delay systems, nonlinear time-delay systems with unknown control direction and nonlinear time-delay systems with un-measurable states. The proposed control schemes can be extended to the adaptive learning control problem for wider classes of nonlinear systems revelent to abovementioned nonlinear systems.The topics presented in this book are research hot spots of iterative learning control. This book will be a valuable reference for researchers and students working or studying in this area.