%0 Conference Paper %1 WebbBrain02 %A Webb, G. I. %A Brain, D. %B Proceedings of the 2002 Pacific Rim Knowledge Acquisition Workshop (PKAW'02) %C Tokyo %D 2002 %E Yamaguchi, T. %E Hoffmann, A. %E Motoda, H. %E Compton, P. %I Japanese Society for Artificial Intelligence %K Generality Occams Razor, %P 117-130 %T Generality is Predictive of Predication Accuracy %X There has been a dearth of research into the relative impacts of alternative high level learning biases. This paper presents two hypotheses about the expected impact of selecting between classification rules of differing levels of generality in the absence of other evidence about their likely relative performance on unseen data. It is argued that the accuracy on unseen data of the more general rule will tend to be closer to that of a default rule for the class than will that of the more specific rule. It is also argued that the accuracy on unseen cases of the more specific rule will tend to be closer to the accuracy obtained on training data than will the accuracy of the more general rule. Experimental evidence is provided in support of these hypotheses. We argue that these hypotheses can be of use in selecting appropriate learning biases to achieve specific learning objectives.

@inproceedings{WebbBrain02, abstract = {There has been a dearth of research into the relative impacts of alternative high level learning biases. This paper presents two hypotheses about the expected impact of selecting between classification rules of differing levels of generality in the absence of other evidence about their likely relative performance on unseen data. It is argued that the accuracy on unseen data of the more general rule will tend to be closer to that of a default rule for the class than will that of the more specific rule. It is also argued that the accuracy on unseen cases of the more specific rule will tend to be closer to the accuracy obtained on training data than will the accuracy of the more general rule. Experimental evidence is provided in support of these hypotheses. We argue that these hypotheses can be of use in selecting appropriate learning biases to achieve specific learning objectives.}, added-at = {2016-03-20T05:42:04.000+0100}, address = {Tokyo}, audit-trail = {*}, author = {Webb, G. I. and Brain, D.}, biburl = {https://www.bibsonomy.org/bibtex/2b1abd8d7aeceeaadcd48ee83b68fdf05/giwebb}, booktitle = {Proceedings of the 2002 {Pacific} Rim Knowledge Acquisition Workshop (PKAW'02)}, editor = {Yamaguchi, T. and Hoffmann, A. and Motoda, H. and Compton, P.}, interhash = {5d1a67b2fbdf52ff2f8e8814348e07d0}, intrahash = {b1abd8d7aeceeaadcd48ee83b68fdf05}, keywords = {Generality Occams Razor,}, location = {Tokyo, Japan}, pages = {117-130}, publisher = {Japanese Society for Artificial Intelligence}, timestamp = {2016-03-20T05:42:04.000+0100}, title = {Generality is Predictive of Predication Accuracy}, year = 2002 }