%0 Conference Paper %1 Webb94b %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 Generality Learning, Occams Razor, Rule %P 60-67 %T Generality Is More Significant Then Complexity: Toward An Alternative To Occams Razor %X Occam's Razor is widely employed in machine learning to select between classifiers with equal empirical support. This paper presents the theorem of decreasing inductive power: that, all other things being equal, if two classifiers a and b cover identical cases from the training set and a is a generalisation of b, a has higher probability than b of misclassifying a previously unsighted case. This theorem suggests that, to the contrary of Occam's Razor, generality, not complexity, should be used to select between classifiers with equal empirical support. Two studies are presented. The first study demonstrates that the theorem of decreasing inductive power holds for a number of commonly studied learning problems and for a number of different means of manipulating classifier generality. The second study demonstrates that generality provides a more consistent indicator of predictive accuracy in the context of a default rule than does complexity. These results suggest that the theorem of decreasing predictive power provides a suitable theoretical framework for the development of learning biases for use in selecting between classifiers with identical empirical support

@inproceedings{Webb94b, abstract = {Occam's Razor is widely employed in machine learning to select between classifiers with equal empirical support. This paper presents the theorem of decreasing inductive power: that, all other things being equal, if two classifiers a and b cover identical cases from the training set and a is a generalisation of b, a has higher probability than b of misclassifying a previously unsighted case. This theorem suggests that, to the contrary of Occam's Razor, generality, not complexity, should be used to select between classifiers with equal empirical support. Two studies are presented. The first study demonstrates that the theorem of decreasing inductive power holds for a number of commonly studied learning problems and for a number of different means of manipulating classifier generality. The second study demonstrates that generality provides a more consistent indicator of predictive accuracy in the context of a default rule than does complexity. These results suggest that the theorem of decreasing predictive power provides a suitable theoretical framework for the development of learning biases for use in selecting between classifiers with identical empirical support}, added-at = {2016-03-20T05:42:04.000+0100}, address = {Singapore}, audit-trail = {*}, author = {Webb, G. I.}, biburl = {https://www.bibsonomy.org/bibtex/2e16df88dfaab6035ef027df95ba20877/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 = {c3b5d7f56b7eccbed9629f73047c9f32}, intrahash = {e16df88dfaab6035ef027df95ba20877}, keywords = {Generality Learning, Occams Razor, Rule}, location = {Armidale,NSW, Australia}, pages = {60-67}, publisher = {World Scientific}, timestamp = {2016-03-20T05:42:04.000+0100}, title = {Generality Is More Significant Then Complexity: Toward An Alternative To Occams Razor}, year = 1994 }