The Utility of Feature Construcuon for Back-Propagation
Proceedings of the Twelfth International Joint Conference on Artificial Intelligence. Learning Be Knowledge Acquisition. Pages 844-849.
Abstract
The ease oflearning concepts from examples in empirical machine learning depends on the attributes used for describing the training data. We show that decision-tree based feature construction can be used to improve the performance of back-propagation (BP), an artificial neural network algorithm, both in terms of the convergence speed and the number of epochs taken by the BP algorithm to converge. We use disjunctive concepts to illustrate feature construction, and describe a measure of feature quality and concept difficulty. We show that a reduction in the difficulty ofthe concepts to be learned by constructing better representations increases the performance of BP considerably.
@inproceedings{ijcai1991p124,
title = {The Utility of Feature Construcuon for Back-Propagation},
author = {Ragavan, Harish and Piramuthu, Selwyn},
booktitle = {Proceedings of the Twelfth International Joint Conference on
Artificial Intelligence, {IJCAI-91}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {John Mylopoulos and Ray Reiter},
pages = {844--849},
year = {1991},
month = {8},
note = {Learning Be Knowledge Acquisition},
url = {https://ijcai.org/proceedings/1991/124},
}
TY - CPAPER TI - The Utility of Feature Construcuon for Back-Propagation AU - Ragavan, Harish AU - Piramuthu, Selwyn T2 - Proceedings of the Twelfth International Joint Conference on Artificial Intelligence, IJCAI-91 PB - International Joint Conferences on Artificial Intelligence PY - 1991 SP - 844 EP - 849 UR - https://ijcai.org/proceedings/1991/124 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
