A model for mixed category perception based on absolute feature values
J. Basak, Sankar Kumar Pal · 2002
Recently, X-tron was developed by Basak et al. (1993, 1995) by considering the task of mixed category perception as a set covering problem where a hypothesis is formed about the presence of a set of objects which would be able to interpret the presence of input features. Here we present a new version of X-tron which is able to accept the absolute values of the features and interpret them even in a mixed form. The range of absolute information of each feature is viewed here as consisting of an unknown number of quantized slots. The degree of presence of a feature corresponding to a category is determined with a membership function. An initial guess is made about the size of the slots. Then the network automatically learns the number of slots and the membership function during the categorisation/self-organisation process.