A neuro-fuzzy computing model of human pattern generation

Investigates a novel technique for constructing and evaluating neuro-fuzzy models of human pattern generation. The modeling approach consists of two steps: first, a neural network is trained to learn a core concept, and then the trained network is augmented with additional processing nodes and connections. The augmented network is then tested on its ability to solve problems related to the core concept for which it was trained. We present results from applying our model to image generation and decision making.