Failure-Driven Reminding for Incremental Learning
Proceedings of the Seventh International Joint Conference on Artificial Intelligence. Learning. Pages 115-119.
Abstract
Much of adult learning is gradual, almost imperceptible. Our model for this knowledge-based, incremental learning is to augment normal story comprehension processing with a failure tracking mechanism. When a comprehension rule fails, the failure and its correction are stored in an exception episode attached to the failing rule. The rule is otherwise unchanged. Subsequent failures of that rule trigger the retrieval of these exception episodes (failure-drivep repipdipg). Rule modification occurs when classes can be found for the known exceptions. The ALFRED program is a preliminary implementation that classifies and remembers failures of "everyday knowledge" in the domain of political economics.
@inproceedings{ijcai1981p25,
title = {Failure-Driven Reminding for Incremental Learning},
author = {Riesbeck, Christopher},
booktitle = {Proceedings of the Seventh International Joint Conference on
Artificial Intelligence, {IJCAI-81}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Roger C. Schank},
pages = {115--119},
year = {1981},
month = {8},
note = {Learning},
url = {https://ijcai.org/proceedings/1981/25},
}
TY - CPAPER TI - Failure-Driven Reminding for Incremental Learning AU - Riesbeck, Christopher T2 - Proceedings of the Seventh International Joint Conference on Artificial Intelligence, IJCAI-81 PB - International Joint Conferences on Artificial Intelligence PY - 1981 SP - 115 EP - 119 UR - https://ijcai.org/proceedings/1981/25 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
