Abstract

The DNA promoter sequences domain theory and database have become popular for testing systems that integrate empirical and analytical learning. This note reports a simple change and reinterpretation of the domain theory in terms of M-of-N concepts, involving no learning, that results in an accuracy of 93.4% on the 106 items of the database. Moreover, an exhaustive search of the space of M-of-N domain theory interpretations indicates that the expected accuracy of a randomly chosen interpretation is 76.5%, and that a maximum accuracy of 97.2% is achieved in 12 cases. This demonstrates the informativeness of the domain theory, without the complications of understanding the interactions between various learning algorithms and the theory. In addition, our results help characterize the difficulty of learning using the DNA promoters theory. 1. Introduction The DNA promoter sequences domain theory and database, contributed by M. Noordewier and J. Shavlik to the UCI repository (Murphy & Aha, 19...

Citations

662	Repository of machine learning databases - Murphy, Aha - 1994
73	Symbolic Knowledge and Neural Networks: Insertion, Refinement and Extraction - Towell
35	Symbolic revision of theories with M-of-N rules - Baffes, Mooney - 1993
35	Bias-Driven Revision of Logical Domain Theories - Koppel, Feldman, et al. - 1994
33	Compilation and analysis of Escherichia coli promoter DNA sequences - Hawley, McClure - 1983
27	Combining connectionist and symbolic learning to refine certainty-factor rule-bases - Mahoney, Mooney - 1993
23	Using ExplanationBased and Empirical Methods in Theory Revision - Ourston - 1991
21	Analysis of E. coli promoter sequences - Harley, Reynolds - 1987
20	Compilation of E. coli mRNA promoter sequences - Lisser, Margalit - 1993
13	Comparing methods for refining certainty-factor rule bases - Mahoney, Mooney - 1994
12	Escherichia Coli Promoters: I. Consensus as it relates to spacing class, specificity, repeat substructure, and three dimensional orgainzation - O'Neill - 1989
9	Bootstrapping training-data representations for inductive learning: “a case study in molecular biology - Hirsh, Japkowicz - 1994
9	Using genetic search to refine knowledge-based neural networks - Opitz, Shavlik - 1994
9	Symbolic revision of theories with M-of-N rules - es, P, et al. - 1993
8	Making the most of what you've got: using models and data to improve learning rate and prediction accuracy - Ortega - 1994
7	Comparing methods for re ning certainty-factor rule-bases - Mahoney, Mooney - 1994
4	Getting the most from flawed theories - Koppel, Segre - 1994
2	Escherichia coli promoters II: A spacing-class dependent promoter search protocol - O'Neill, Chiafari - 1989
2	Getting the most from awed theories - Koppel, Segre, et al. - 1994
1	On the Informativeness of the DNA Promoter Sequences Domain Theory - Norton - 1994
1	Using neural networks to refine existing biological knowledge - thesis - 1992
1	Using genetic search to re ne knowledge-based neural networks - Opitz, Shavlik - 1994
1	Using neural networks to re ne existing biological knowledge - Shavlik, Towell, et al. - 1992