Incremental Non-unanimous Concept Reformation through Queried Object Classification

Abstract

Given a set of observations or new information, agents should be able to update their understandings of the world. As a part of any agents' world ontology, concepts need to evolve in time. In this paper we present a new representation for non-unanimous concepts based on the combination of feature-values and their probabilities. This representation leads us to incrementally evolve the concepts upon facing with new observations or information. As agents' access to the knowledge structure of the peer agents is limited due to the high cost of communication, we enabled our agents to use any queried object and update the previously calculated probability of every feature-value combination based on the probability of that object being an instance of a concept.