Premium
A Neural Network Model for Attribute‐Based Decision Processes
Author(s) -
Usher Marius,
Zakay Dan
Publication year - 1993
Publication title -
cognitive science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.498
H-Index - 114
eISSN - 1551-6709
pISSN - 0364-0213
DOI - 10.1207/s15516709cog1703_2
Subject(s) - generalization , artificial neural network , computer science , scalability , attractor , simple (philosophy) , selection (genetic algorithm) , decision model , artificial intelligence , machine learning , mathematics , mathematical analysis , philosophy , epistemology , database
We propose a neural model of multiattribute‐decision processes, based on an attractor neural network with dynamic thresholds. The model may be viewed as a generalization of the elimination by aspects model, whereby simultaneous selection of several aspects is allowed. Depending on the amount of synaptic inhibition, various kinds of scanning strategies may be performed, leading in some cases to vacillations among the alternatives. The model predicts that decisions of a longer time duration exhibit a lower violation of the simple scalability law, as opposed to shorter decisions. Furthermore, the model is suggested as a general attribute‐based decision module. Accordingly, various decision strategies are manifested depending on the module's parameters.