%0 Conference Paper %1 YipWebb94a %A Yip, S. %A Webb, G. I. %B Artificial Intelligence: Sowing the Seeds for the Future, Proceedings of Seventh Australian Joint Conference on Artificial Intelligence (AI'94) %C Singapore %D 1994 %E Zhang, C. %E Debenham, J. %E Lukose, D. %I World Scientific %K Constructive Induction %P 29-36 %T Empirical Function Attribute Construction in Classification Learning %X The merits of incorporating feature construction to assist selective induction in learning hard concepts are well documented. This paper introduces the notion of function attributes and reports a method of incorporating functional regularities in classifiers. Training sets are preprocessed with this method before submission to a selective induction classification learning system. The method, referred to as FAFA (function attribute finding), is characterised by finding bivariate functions that contribute to the discrimination between classes and then transforming them to function attributes as additional attributes of the data set. The value of each function attribute equals the deviation of each example from the value obtained by applying that function to the example. The expanded data set is then submitted to classification learning. Evaluation with published and artificial data shows that this method can improve classifiers in terms of predictive accuracy and complexity.

@inproceedings{YipWebb94a, abstract = {The merits of incorporating feature construction to assist selective induction in learning hard concepts are well documented. This paper introduces the notion of function attributes and reports a method of incorporating functional regularities in classifiers. Training sets are preprocessed with this method before submission to a selective induction classification learning system. The method, referred to as FAFA (function attribute finding), is characterised by finding bivariate functions that contribute to the discrimination between classes and then transforming them to function attributes as additional attributes of the data set. The value of each function attribute equals the deviation of each example from the value obtained by applying that function to the example. The expanded data set is then submitted to classification learning. Evaluation with published and artificial data shows that this method can improve classifiers in terms of predictive accuracy and complexity.}, added-at = {2016-03-20T05:42:04.000+0100}, address = {Singapore}, audit-trail = {*}, author = {Yip, S. and Webb, G. I.}, biburl = {https://www.bibsonomy.org/bibtex/2c24a493b1e7575685d8625052b223296/giwebb}, booktitle = {Artificial Intelligence: Sowing the Seeds for the Future, Proceedings of Seventh Australian Joint Conference on Artificial Intelligence (AI'94)}, editor = {Zhang, C. and Debenham, J. and Lukose, D.}, interhash = {c60356d55c4d1a93919b760ee9e0d9bb}, intrahash = {c24a493b1e7575685d8625052b223296}, keywords = {Constructive Induction}, location = {Armidale,NSW, Australia}, pages = {29-36}, publisher = {World Scientific}, timestamp = {2016-03-20T05:42:04.000+0100}, title = {Empirical Function Attribute Construction in Classification Learning}, year = 1994 }