Induction of Relational Productions in the Presence of Background Information
Proceedings of the Fifth International Joint Conference on Artificial Intelligence. Knowledge Acquisition. Pages 349-354.
Abstract
An operational theory is developed for the generalization of relational productions in the presence of background information. This provides a unified theoretical solution for a broad class of intelligence paradigms, including letter sequence completion, visual analogies, and the learning of operators from before-and-after situation pairs or from situation sequences . Relational productions are used as a formal model for operators. The generalization process is given access to a common body of background information. Background literals which have association chains to foreground literals may be incorporated into the generalization. This theory has been computer implemented in SNOBOL4, and examples illustrate its application in the four paradigms mentioned above .
@inproceedings{ijcai1977p82,
title = {Induction of Relational Productions in the Presence of Background Information},
author = {Vere, Steven A.},
booktitle = {Proceedings of the Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-77}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Raj Reddy},
pages = {349--354},
year = {1977},
note = {Knowledge Acquisition},
url = {https://ijcai.org/proceedings/1977/82},
}
TY - CPAPER TI - Induction of Relational Productions in the Presence of Background Information AU - Vere, Steven A. T2 - Proceedings of the Fifth International Joint Conference on Artificial Intelligence, IJCAI-77 PB - International Joint Conferences on Artificial Intelligence PY - 1977 SP - 349 EP - 354 UR - https://ijcai.org/proceedings/1977/82 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
