Overview
An essential capacity of intelligence is the ability to learn. An artificially intelligent system that could learn would not have to be programmed for every eventuality; it could adapt to its changing environment and conditions just as biological systems do. Illustrating Evolutionary Computation with Mathematica introduces evolutionary computation to the technically savvy reader who wishes to explore this fascinating and increasingly important field. Unique among books on evolutionary computation, the book also explores the application of evolution to developmental processes in nature, such as the growth processes in cells and plants. If you are a newcomer to the evolutionary computation field, an engineer, a programmer, or even a biologist wanting to learn how to model the evolution and coevolution of plants, this book will provide you with a visually rich and engaging account of this complex subject.
* Introduces the major mechanisms of biological evolution.
* Demonstrates many fascinating aspects of evolution in nature with simple, yet illustrative examples.
* Explains each of the major branches of evolutionary computation: genetic algorithms, genetic programming, evolutionary programming, and evolution strategies.
* Demonstrates the programming of computers by evolutionary principles using Evolvica, a genetic programming system designed by the author.
* Shows in detail how to evolve developmental programs modeled by cellular automata and Lindenmayer systems.
* Provides Mathematica notebooks on the Web that include all the programs in the book and supporting animations, movies, and graphics.
"...explores the entire domain of evolutionary computation which software professionals & AI researchers & students will appreciate utilizing the companion Web site to explore & experiment the algorithms & programming approaches."
Editorials
Jack J. Woehr
Illustrating Evolutionary Computation with Mathematica, by Christian Jacob, is the English translation of the German original, Pricipia Evolvica, Simulierte Evolution mit Mathematica (dpunkt.verlag 1997).Presenting to us the intriguing yet stilted artwork generated by evolutionary algorithms, Principia says interesting things about our ability to represent the world digitally, things of interest not just to specialists in the field, but to every serious programmer. Furthermore, computer caricature of the processes from which arise all life on earth is fraught with existential ambiguity in light of concurrent advances in biotechnology. The battle of Waterloo was won on the playing fields of Eton, one might say.
I don't mean to imply that this is a book of computer art. Principia is a masterpiece of a computer-science text. It's about programmers discovering ways to splash the gene pool of an evolving system and speed up the rate of evolution towards the desired computational result. Mutation, selection ... and what happens when the drift isn't in the desired direction? Smash it! Randomize afresh. This sheds new light on the Flood as eugenics.
While genetic algorithms are not new, it's startling to see how far a computer scientist can go towards explaining his thought processes in terms of Darwin. Breaking down complex problems into evolutionary algorithms requires an understanding of evolution as it occurred in the tangible world. There's an underlying principle here, as the Greeks used to say, one that has even political import when you consider there are school boards which believe science can be taught without teaching evolution.
Evolvica (http://www2.informatik.uni-erlangen.de/~jacob/Evolvica/Evolvica-Intro.html) is a Mathematica-based tutorial, programming, and experimentation environment for evolutionary computing that was created by the author and contains the examples in the book. It can be downloaded from http://www.cpsc.ucalgary.ca/njacob/IEC. If you don't own a license for Mathematica, there's the MathReader viewer for Mathematica which lets you view the system and examples; download it from http://www.wolfram.com/products/mathreader/.
The richness of Illustrating Evolutionary Computation with Mathematica has to be seen rather than described. I can't pretend to have finished this book; it will sit on my bedside bookshelf for years, no doubt, to be thumbed through a few of its 575 pages at a time and the wealth of ideas, equations, models and illustrative examples savored and assimilated.
Morgan Kaufmann Publishers went all out on this one, the layout is both lavish and tidy. That's only what this book deserved, which must have been at least half a decade in the authoring. If you have any interest in genetic algorithms, cellular automata, or simulated annealing this is the must-read of the year.
— ercb.com