Knowledge Incorporation in Evolutionary Computation / Edition 1

by Yaochu Jin

Overview

Incorporation of a priori knowledge, such as expert knowledge, meta-heuristics and human preferences, as well as domain knowledge acquired during evolu­ tionary search, into evolutionary algorithms has received increasing interest in the recent years. It has been shown from various motivations that knowledge incorporation into evolutionary search is able to significantly improve search efficiency. However, results on knowledge incorporation in evolution­ ary computation have been scattered in a wide range of research areas and a systematic handling of this important topic in evolutionary computation still lacks. This edited book is a first attempt to put together the state-of-art and re­ cent advances on knowledge incorporation in evolutionary computation within a unified framework. Existing methods for knowledge incorporation are di­ vided into the following five categories according to the functionality of the incorporated knowledge in the evolutionary algorithms. 1. Knowledge incorporation in representation, population initialization, - combination and mutation. 2. Knowledge incorporation in selection and reproduction. 3. Knowledge incorporation in fitness evaluations. 4. Knowledge incorporation through life-time learning and human-computer interactions. 5. Incorporation of human preferences in multi-objective evolutionary com­ putation. The intended readers of this book are graduate students, researchers and practitioners in all fields of science and engineering who are interested in evolutionary computation. The book is divided into six parts. Part I contains one introductory chapter titled "A selected introduction to evolutionary computation" by Yao, which presents a concise but insightful introduction to evolutionary computation.

Product Details

ISBN-13:	9783642061745
Publisher:	Springer Berlin Heidelberg
Publication date:	12/16/2010
Series:	Studies in Fuzziness and Soft Computing , #167
Edition description:	2005
Pages:	548
Product dimensions:	6.10(w) x 9.25(h) x 0.24(d)

Table of Contents

I Introduction.- A Selected Introduction to Evolutionary Computation.- II Knowledge Incorporation in Initialization, Recombination and Mutation.- The Use of Collective Memory in Genetic Programming.- A Cultural Algorithm for Solving the Job Shop Scheduling Problem.- Case-Initialized Genetic Algorithms for Knowledge Extraction and Incorporation.- Using Cultural Algorithms to Evolve Strategies in A Complex Agent-based System.- Methods for Using Surrogate Models to Speed Up Genetic Algorithm Optimization: Informed Operators and Genetic Engineering.- Fuzzy Knowledge Incorporation in Crossover and Mutation.- III Knowledge Incorporation in Selection and Reproduction.- Learning Probabilistic Models for Enhanced Evolutionary Computation.- Probabilistic Models for Linkage Learning in Forest Management.- Performance-Based Computation of Chromosome Lifetimes in Genetic Algorithms.- Genetic Algorithm and Case-Based Reasoning Applied in Production Scheduling.- Knowledge-Based Evolutionary Search for Inductive Concept Learning.- An Evolutionary Algorithm with Tabu Restriction and Heuristic Reasoning for Multiobjective Optimization.- IV Knowledge Incorporation in Fitness Evaluations.- Neural Networks for Fitness Approximation in Evolutionary Optimization.- Surrogate-Assisted Evolutionary Optimization Frameworks for High-Fidelity Engineering Design Problems.- Model Assisted Evolution Strategies.- V Knowledge Incorporation through Life-time Learning and Human-Computer Interactions.- Knowledge Incorporation Through Lifetime Learning.- Local Search Direction for Multi-Objective Optimization Using Memetic EMO Algorithms.- Fashion Design Using Interactive Genetic Algorithm with Knowledge-based Encoding.- Interactive Evolutionary Design.- VI Preference Incorporation in Multi-objective Evolutionary Computation.- Integrating User Preferences into Evolutionary Multi-Objective Optimization.- Human Preferences and their Applications in Evolutionary Multi—Objective Optimization.- An Interactive Fuzzy Satisficing Method for Multi-objective Integer Programming Problems through Genetic Algorithms.- Interactive Preference Incorporation in Evolutionary Engineering Design.