Fuzzy neural tree in evolutionary computation for architectural design cognition

Abstract

A novel fuzzy-neural tree (FNT) is presented. Each tree node uses a Gaussian as a fuzzy membership function, so that the approach uniquely is in align with both the probabilistic and possibilistic interpretations of fuzzy membership. It provides a type of logical operation by fuzzy logic (FL) in a neural structure in the form of rule-chaining, yielding a novel concept of weighted fuzzy logical AND and OR operation. The tree can be supplemented both by expert knowledge, as well as data set provisions for model formation. The FNT is described in detail pointing out its various potential utilizations demanding complex modeling and multi-objective optimization therein. One of such demands concerns cognitive computing for design cognition. This is exemplified and its effectiveness is demonstrated by computer experiments in the realm of Architectural design.