8. Parameter Control

The issue of setting the values of evolutionary algorithm parameters before running an EA was treated in the previous chapter. In this chapter we discuss how to do this during a run of an EA, in other words, we elaborate on controlling EA parameters on-the-fly. This has the potential of adjusting the algorithm to the problem while solving the problem. We provide a classification of different approaches based on a number of complementary features and present examples of control mechanisms for every major EA component. Thus we hope to both clarify the points we wish to raise and also to give the reader a feel for some of the many possibilities available for controlling different parameters.

Contents:
8.1 Introduction ……………………………………..131
8.2 Examples of Changing Parameters…………………….132
8.2.1 Changing the Mutation Step Size………………..133
8.2.2 Changing the Penalty Coefficients ……………….134
8.3 Classification of Control Techniques……………………136
8.3.1 What Is Changed?……………………………136
8.3.2 How Are Changes Made?………………………136
8.3.3 What Evidence Informs the Change?……………..138
8.3.4 What Is the Scope of the Change? ……………….138
8.3.5 Summary…………………………………..139
8.4 Examples of Varying EA Parameters…………………..139
8.4.1 Representation………………………………139
8.4.2 Evaluation Function ………………………….140
8.4.3 Mutation…………………………………..141
8.4.4 Crossover ………………………………….141
8.4.5 Selection …………………………………..142
8.4.6 Population …………………………………142
8.4.7 Varying Several Parameters Simultaneously . . . . . . . . . . . 143
8.5 Discussion……………………………………….144

Suggested Reading

Exercises

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>

The on-line accompaniment to the book Introduction to Evolutionary Computing