At present, it is not clear whether the appeal of genetic algorithms arises from their performance or from their aesthetically pleasing origins in the theory of evolution. Much work remains to be done to identify the conditions under which genetic algorithms perform well.
Ooo burn. That put those uppity genetic algorithm people in their place.
Apart from being unafraid to put the hurt on GA wannabe playas, and their thoughtful apology to Romanian readers to who are familiar with the placenames of Romania and therefore will be able only indirectly to appreciate the travelling-in-Romania analogy, another way to tell the high quality of Russell and Norvig’s Artificial Intelligence textbook is to examine the picture on the cover.
It is a computer-rendered picture of an office, and the office is cluttered with pictures of Alan Turing, and Shakey the Robot, and bits of paper with different AI notations on them, and a miscellaneous collection of other things that computer scientists think are cool. No attempt has been made to come up with a unifying image for the subject, an endeavour most academics achieve by the simple expedient of selecting a Magritte painting at random. Crucially, the picture includes the book itself, with the cover showing a smaller copy of the book in a fashion representing infinite regress.
Clearly, this is a naff picture. So naff is the picture that it conveys the unmistakable message “so great is this textbook that it requires no attractive cover design: anyone who is put off by the naff picture is not worthy of its contents”.
This is, I think, a generally applicable rule: naff picture, good textbook.