Just enough learning (of association rules): the TAR2 “Treatment” learner

An over-zealous machine learner can automatically generate large, intricate, theories which can be hard to understand. However, such intricate learning is not necessary in domains that lack complex relationships. A much simpler learner can suffice in domains with narrow funnels; i.e. where most domain variables are controlled by a very small subset. Such a learner is TAR2: a weighted-class minimal contrast-set association rule learner that utilizes confidence-based pruning, but not support-based pruning. TAR2 learns treatments; i.e. constraints that can change an agent’s environment. Treatments take two forms. Controller treatments hold the smallest number of conjunctions that most improve the current state of the system. Monitor treatments hold the smallest number of conjunctions that best detect future faulty system behavior. Such treatments tell an agent what to do (apply the controller) and what to watch for (the monitor conditions) within the current environment. Because TAR2 generates very small theories, our experience has been that users prefer its tiny treatments. The success of such a simple learner suggests that many domains lack complex relationships.

[1]  Ellis Horowitz,et al.  Cocomo ii model definition manual , 1998 .

[2]  Tim Menzies,et al.  Constraining discussions in requirements engineering , 2001 .

[3]  Stephen D. Bay,et al.  Detecting change in categorical data: mining contrast sets , 1999, KDD '99.

[4]  Wynne Hsu,et al.  Integrating Classification and Association Rule Mining , 1998, KDD.

[5]  Alan Smaill,et al.  Backbone Fragility and the Local Search Cost Peak , 2000, J. Artif. Intell. Res..

[6]  Tim Menzies,et al.  Practical large scale what-if queries: case studies with software risk assessment , 2000, Proceedings ASE 2000. Fifteenth IEEE International Conference on Automated Software Engineering.

[7]  Ke Wang,et al.  Mining confident rules without support requirement , 2001, CIKM '01.

[8]  James M. Crawford,et al.  Experimental Results on the Application of Satisfiability Algorithms to Scheduling Problems , 1994, AAAI.

[9]  Bashar Nuseibeh,et al.  An empirical investigation of multiple viewpoint reasoning in requirements engineering , 1999, Proceedings IEEE International Symposium on Requirements Engineering (Cat. No.PR00188).

[10]  Robert C. Holte,et al.  Very Simple Classification Rules Perform Well on Most Commonly Used Datasets , 1993, Machine Learning.

[11]  J. Dekleer.  An assumption-based TMS , 1986 .

[12]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[13]  Tim Menzies,et al.  Data Mining for Very Busy People , 2003, Computer.

[14]  Tim Menzies,et al.  Applications of abduction: hypothesis testing of neuroendocrinological qualitative compartmental models , 1997, Artif. Intell. Medicine.

[15]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[16]  Ramakrishnan Srikant,et al.  Fast Algorithms for Mining Association Rules in Large Databases , 1994, VLDB.

[17]  Tim Menzies,et al.  Converging on the optimal attainment of requirements , 2002, Proceedings IEEE Joint International Conference on Requirements Engineering.

[18]  Geoffrey I. Webb.  Efficient search for association rules , 2000, KDD '00.

[19]  Tim Menzies,et al.  Many Maybes Mean (Mostly) the Same Thing , 2004 .

[20]  Ron Rymon.  An SE-tree-based prime implicant generation algorithm , 2005, Annals of Mathematics and Artificial Intelligence.

[21]  Tim Menzies,et al.  Reusing Models For Requirements Engineering , 2001 .

[22]  金田 重郎,et al.  C4.5: Programs for Machine Learning (書評) , 1995 .

[23]  Ying Hu,et al.  TREATMENT LEARNING: IMPLEMENTATION AND APPLICATION , 2003 .

[24]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[25]  Bojan Cukic,et al.  Adequacy of Limited Testing for Knowledge Based Systems , 2000, Int. J. Artif. Intell. Tools.

[26]  Ada Wai-Chee Fu,et al.  Mining association rules with weighted items , 1998, Proceedings. IDEAS'98. International Database Engineering and Applications Symposium (Cat. No.98EX156).

[27]  Johan de Kleer,et al.  An Assumption-Based TMS , 1987, Artif. Intell..

[28]  Martin S. Feather,et al.  Combining the best attributes of qualitative and quantitative risk management tool support , 2000, Proceedings ASE 2000. Fifteenth IEEE International Conference on Automated Software Engineering.

[29]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[30]  Ron Rymon.  An SE-tree based Characterization of the Induction Problem , 1993, ICML.

[31]  Robyn R. Lutz.  Bi-directional Analysis for Certification of Safety-Critical Software , 1999 .

[32]  Raymond J. Madachy,et al.  Heuristic Risk Assessment Using Cost Factors , 1997, IEEE Softw..

[33]  James M. Crawford,et al.  Lifted Search Engines for Satis ability , 2007 .

[34]  Tim Menzies,et al.  Agents in a Wild World , 2006 .

[35]  Benjamin Kuipers,et al.  Model Decomposition and Simulation: A Component Based Qualitative Simulation Algorithm , 1997, AAAI/IAAI.

[36]  Ramakrishnan Srikant,et al.  Fast algorithms for mining association rules , 1998, VLDB 1998.

[37]  Johan de Kleer,et al.  Extending the ATMS , 1986, Artif. Intell..

[38]  Bojan Cukic,et al.  Caveats , 2020, The African Continental Free Trade Area: Economic and Distributional Effects.

[39]  B. Cukic,et al.  Testing nondeterminate systems , 2000, Proceedings 11th International Symposium on Software Reliability Engineering. ISSRE 2000.