Other bottom-up techniques

Distributed computing/ distributed AI Compared with connectionist systems, the computational nodes here have greater power, and communication can be of many more kinds.

See Semantic web, Intelligent agents.

Evolutionary programming Special cases: genetic algorithms, cellular automata, A-life - intelligence as emergent feature of living systems?

Alan Turing The Chemical Basis of Morphogenesis, 1952) - development of biological form by the mechanism of two or more chemicals diffusing at different rates - he showed that the resulting diffusion ``waves'' of differential concentrations could lead to development of repetitive structures; in 3D they could cause embryonic gartrulation.

John von Neumann studied cellular automata and generation of order in them from following simple rules. He defined the computational features of reproduction, realising (years before the discovery of DNA) that a self-replicating system must function as instruction as well as data, and that errors in copying the self-description could lead to evolution.

Genetic Algorithm: Functions by generating a large set of possible solutions to a given problem. It then evaluates each of those solutions, and decides on a ``fitness level'' (depending on how close the solution is to the answer) for each solution set. These solutions then breed new solutions by mating which involves ``crossing over'' of genes. The parent solutions that are more ``fit'' are more likely to reproduce, while those that are less ``fit'' are less likely to do so. Solutions are evolved over time. Genetic algorithms can be highly efficient if programmed correctly. (See biomorph example in Richard Dawkins: The Blind Watchmaker.)

Evolutionary programming is often used in conjunction with other areas of AI such as neural networks. GAs are sometimes used to evolve neural network architectures or weights, or are used to fine-tune parameters in finite-state machines (in gaming).

Situated models (more in sec. )

• Distributed models, everyday cognition sec. .

• Situated robotics (Rodney Brooks)

• Situated action (see spl issue of Cog. Sci., 1993)

Models in abnormal psychology: Neurotic anxiety, fugue, hysterical paralysis, MPD.

Models in creativity (Boden)