Toward a Learning of Object Models Using Analogical Objects and Verbal Instruction

Norihiro Abe, Fumihide Itoh, Saburo Tsuji

In this paper an attempt of analogical learning method by verbalism is shown in order to create a model for an identification of unknown objects. When we expect a computer to recognize objects, the models of them must be given to it, however there are cases where some objects may not be matched to the models or there is no model with which object is compared. At that time, this system can augment or create new descriptions by making use of explicit verbal instructions.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.