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

Application Systems

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 2

Medical

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.