Learning by Controlled Transference of Knowledge Between Domains
Proceedings of the Eighth International Joint Conference on Artificial Intelligence. Learning and Knowledge Acquisition. Pages 439-442.
Abstract
A method for Learning by practice, based on the transference of knowledge between doma1ns, is discussed and illustrated in the context of a problem solver functioning in a domain of elementary physics. As an example of the applicat1on of this approach, it is shown how knowledge belonging to the doma1n of "symmetry of figures" can be successfully used to solve problems in the first domain. This controlled transference of knowledge is accomplished in four steps: a) mapping certain components of the physics problem into the domain of figures, b) applying the available knowledge for that domain, c) mapping the results back into the original domain, and d) testing the validity of the transference.
@inproceedings{ijcai1983p107,
title = {Learning by Controlled Transference of Knowledge Between Domains},
author = {Araya, Agustin A.},
booktitle = {Proceedings of the Eighth International Joint Conference on
Artificial Intelligence, {IJCAI-83}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Alan Bundy},
pages = {439--442},
year = {1983},
note = {Learning and Knowledge Acquisition},
url = {https://ijcai.org/proceedings/1983/107},
}
TY - CPAPER TI - Learning by Controlled Transference of Knowledge Between Domains AU - Araya, Agustin A. T2 - Proceedings of the Eighth International Joint Conference on Artificial Intelligence, IJCAI-83 PB - International Joint Conferences on Artificial Intelligence PY - 1983 SP - 439 EP - 442 UR - https://ijcai.org/proceedings/1983/107 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
