FEBAMSOM-BAM*: Neural network model of human categorization of the N-bits parity problem
Laurence Morissette, Sylvain Chartier · 2013
Classification following a non-linearly separable boundary is a cognitive task that is hard to complete for humans and animals. Feedforward neural networks are able to perform the task efficiently but they present little correspondence with human cognition. We present a neural network model of human categorization of the n-bit parity problem, using a modification of the pi-sigma network incorporating bidirectional associative memories and self-organizing maps. The model has good cognitive validity with cognitive human processes and is efficient.