A Learning System Which Accommodates Feature Interactions
Proceedings of the Eighth International Joint Conference on Artificial Intelligence. Learning and Knowledge Acquisition. Pages 469-471.
Abstract
The author's state-space learning system has effectively optimized the coefficients of linear evaluation functions. The incremental approach uses statistical performance measures from completed solutions to bootstrap the heuristic, which estimates probability of task usefulness. These statistics are clustered in feature space, forming a mediating knowledge structure (region set) between the direct performance measures and the generalized evaluation function. The regions are data-determined, insensitive to noise, and allow management of interacting features through natural piecewise linearity. Early experiment with nonlinearity indicates stability, flexibility and improved task performance.
@inproceedings{ijcai1983p115,
title = {A Learning System Which Accommodates Feature Interactions},
author = {Rendell, Larry 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 = {469--471},
year = {1983},
note = {Learning and Knowledge Acquisition},
url = {https://ijcai.org/proceedings/1983/115},
}
TY - CPAPER TI - A Learning System Which Accommodates Feature Interactions AU - Rendell, Larry A. T2 - Proceedings of the Eighth International Joint Conference on Artificial Intelligence, IJCAI-83 PB - International Joint Conferences on Artificial Intelligence PY - 1983 SP - 469 EP - 471 UR - https://ijcai.org/proceedings/1983/115 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
