An Introduction to Genetic Algorithms - Boente
An Introduction to Genetic Algorithms - Boente
An Introduction to Genetic Algorithms - Boente
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
3.<br />
4.<br />
5.<br />
6.<br />
Write a few paragraphs explaining as clearly and succinctly as possible (a) the Baldwin effect, (b)<br />
how Hin<strong>to</strong>n and Nowlan's results demonstrate it, (c) how Ackley and Littman's results demonstrate it,<br />
and (d) how Ackley and Littman's approach compares with that of Hin<strong>to</strong>n and Nowlan.<br />
Given the description of Echo in section 3.3, think about how Echo could be used <strong>to</strong> model the<br />
Baldwin effect. Design an experiment that might demonstrate the Baldwin effect.<br />
Given the description of Echo in section 3.3, design an experiment that could be done in Echo <strong>to</strong><br />
simulate sexual selection and <strong>to</strong> compare its strength with that of natural selection.<br />
Is Bedau and Packard's "evolutionary activity" measure a good method for measuring adaptation?<br />
Why or why not?<br />
Think about how Bedau and Packard's "evolutionary activity" measure could be used in Echo. What<br />
kinds of "usage" statistics could be recorded, and which of them would be valuable?<br />
Computer Exercises<br />
1.<br />
2.<br />
Write a genetic algorithm <strong>to</strong> replicate Hin<strong>to</strong>n and Nowlan's experiment. Make plots from your results<br />
similar <strong>to</strong> those in figure 3.4, and compare your plots with that figure. Do a run that goes for 2000<br />
generations. At what frequency and at what generation do the question marks reach a steady state?<br />
Could you roughly predict this frequency ahead of time?<br />
Run a GA on the fitness function f(x) = the number of ones in x, where x is a chromosome of length<br />
20. (See computer exercise 1 in chapter 1 for suggested parameters.) Compare the performance of the<br />
GA on this problem with the performance of a modified GA with the following form of sexual<br />
selection:<br />
a.<br />
Add a bit <strong>to</strong> each string in the initial population indicating whether the string is "male" (0) or<br />
"female" (1). (This bit should not be counted in the fitness evaluation.) Initialize the<br />
population with half females and half males.<br />
b.<br />
Separate the two populations of males and females.<br />
c.<br />
Chapter 3: <strong>Genetic</strong> <strong>Algorithms</strong> in Scientific Models<br />
Choose a female with probability proportional <strong>to</strong> fitness. Then choose a male with probability<br />
proportional <strong>to</strong> fitness. Assume that females prefer males with more zeros: the probability that<br />
a female will agree <strong>to</strong> mate with a given male is a function of the number of zeros in the male<br />
(you should define the function). If the female agrees <strong>to</strong> mate, form two offspring via<br />
single−point crossover, and place the male child in the next generation's male population and<br />
85