An in-depth description of Copycat, one of the projects at Douglas Hofstadter's Fluid Analogies Research Group
This promised to be a very interesting book, but it was let down for me by being too low level -- too much about the scientific and technological bases, and not enough about any new computational paradigms. (The very poor level of proof reading, with some chapters thick with spelling mistakes, also detracts.)
I was hoping for an overview of what new tools are being added to our computational capability, with maybe a review of the current state of the art, but what I got was a bunch of essays that have an idiosyncratic viewpoint, with all the details in the wrong places (for me, at least).
For example, the chapter on Genetic Algorithms devotes hardly any space to the schemata model (beyond saying it is intuitive) but instead develops a "statistical mechanics" model, without then providing the intuition of how this model helps us to cast or solve new computational problems. It also seems to imply that mutation is the key concept, with cross-over just an interesting second order add-on (whereas the study of genetic algorithms has shown is that cross-over is key, with mutation playing a surprisingly small role).
The two chapters on quantum computing range over the theoretical QM underpinnings, and the current technology, but again provide no intuition of how these devices work as computers. (And the second of these chapters has an almost useless bibliography, since it omits the papers' titles.)
So I was left disappointed.
Contents
Contents