This paper discusses a technique that uses several different networks working together to find a relationship that approximates analogue training sets. Each network learns a different region of the training space and all these regions fit together, like pieces of a jigsaw puzzle, to cover the entire training space. This analogue approach is an extension to a technique previously developed for solving digital problems. The networks can be of any type (eg backprop, cascade). However, virtually any other technique can be used in place of the networks: evolved polynomials, DRS, Taboo search, Nearest Neighbour, and other statistical techniques.
Lecture Notes in Computer Science : Methodology and Tools in Knowledge-Based Systems : Proceedings 11th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems (IEA-98-AIE), Benicassim, Castellon, Spain, 01-04 June 1998,
Vol. 1415, p. 625-631