JavaScript or Explanation Based Neural Network Learning

JavaScript: Complete Concepts and Techniques, Second Edition

Author: Gary B Shelly

Part of the highly successful Shelly Cashman series, this text offers a step-by-step, screen-by-screen approach and extensive hands-on projects for meaningful learning of JavaScript.

Interesting textbook: Estratégias de Entrada de Mercados Internacionais

Explanation-Based Neural Network Learning: A Lifelong Learning Approach

Author: Sebastian Thrun

Lifelong learning addresses situations in which a learner faces a series of different learning tasks providing the opportunity for synergy among them. Explanation-based neural network learning (EBNN) is a machine learning algorithm that transfers knowledge across multiple learning tasks. When faced with a new learning task, EBNN exploits domain knowledge accumulated in previous learning tasks to guide generalization in the new one. As a result, EBNN generalizes more accurately from less data than comparable methods. Explanation-Based Neural Network Learning: A Lifelong Learning Approach describes the basic EBNN paradigm and investigates it in the context of supervised learning, reinforcement learning, robotics, and chess.

Booknews

Describes a paradigm for machine learning that may open a new generation of methods, especially for situations in which a series of different learning tasks provides an opportunity for synergy among them. The explanation-based neural network approach transfers knowledge across multiple learning tasks, allowing domain knowledge accumulated in previous learning efforts to guide generalization in new learning tasks. The result is more accurate generalizations with less data than previous methods. The method is demonstrated in contexts of supervised learning, reinforced learning, robotics, and chess. Annotation c. by Book News, Inc., Portland, Or.

Table of Contents:

	Foreword
	Preface
1	Introduction	1
2	Explanation-Based Neural Network Learning	19
3	The Invariance Approach	49
4	Reinforcement Learning	93
5	Empirical Results	131
6	Discussion	177
	A An Algorithm for Approximating Values and Slopes with Artificial Neural Networks	195
	B Proofs of the Theorems	203
	C Example Chess Games	207
	References	227
	List of Symbols	253
	Index	259