Experiments on the supervised learning algorithm for formal concept elicitation by cognitive robots

Abstract

Concept elicitation is a fundamental methodology for knowledge extraction and representation in cognitive robot learning. Traditional machine learning technologies deal with object identification, cluster classification, functional regression, and behavior acquisition. This paper presents a supervised machine knowledge learning methodology for concept elicitation from sample dictionaries in natural languages. Formal concepts are autonomously generated based on collective intention of attributes and collective extension of objects elicited from informal definitions in dictionaries. A system of formal concept generation for a cognitive robot is implemented by the Algorithm of Machine Concept Elicitation (AMCE) in MATLAB. Experiments on machine learning for creating a set of twenty formal concepts reveal that the cognitive robot is able to learn synergized concepts in human knowledge in order to build its own cognitive knowledge base. The results of machine-generated concepts demonstrate that the AMCE algorithm can over perform human knowledge expressions in dictionaries in terms of relevance, accuracy, quantitativeness, and cohesiveness.