An experimental comparison of symbolic and connectionist learning algorithms

An experimental comparison of symbolic and connectionist learning algorithms (1989)

by Raymond Mooney , Jude Shavlik

Venue:	Proceedings of the Eleventh International Joint Conference on Artificial Intelligence
Citations:	82 - 6 self

Datum	Value	Source
TITLE	An experimental comparison of symbolic and connectionist learning algorithms	INFERENCE
AUTHOR NAME	Raymond Mooney	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Sciences; University of Texas	SVM HeaderParse 0.2
AUTHOR ADDR	Austin, TX 78712	SVM HeaderParse 0.2
AUTHOR NAME	Jude Shavlik	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Sciences; University of Wisconsin	SVM HeaderParse 0.2
AUTHOR ADDR	Madison, WI 53706	SVM HeaderParse 0.2
ABSTRACT	Despite the fact that many symbolic and connectionist (neural net) learning algorithms are addressing the same problem of learning from classified examples, very little Is known regarding their comparative strengths and weaknesses. This paper presents the results of experiments comparing the ID3 symbolic learning algorithm with the perceptron and back-propagation connectionist learning algorithms on several large real-world data sets. The results show that ID3 and perceptron run significantly faster than does backpropagation, both during learning and during classification of novel examples. However, the probability of correctly classifying new examples is about the same for the three systems. On noisy data sets there is some indication that backpropagation classifies more accurately. 1.	SVM HeaderParse 0.2
YEAR	1989	INFERENCE
VENUE	Proceedings of the Eleventh International Joint Conference on Artificial Intelligence	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	775--780	INFERENCE
CITATIONS	20 found	ParsCit 1.0