Aspects of Intelligent Systems Explanation

Intelligent systems encompass a wide range of software technologies including heuristic and normative expert systems, case-based reasoning systems, and neural networks. This field has been augmented in recent years by Web-based applications, such as recommender systems and the semantic Web. The uses of explanation facilities have their roots in heuristic rule-based expert systems and have long been touted as an important adjunct in intelligent decision support systems. However, in recent years, their uses have been explored in many other intelligent system technologies - particularly those making an impact in e-commerce such as recommender systems. This paper shows how explanation facilities work with a range of symbolic intelligent techniques and, when carefully designed, provide a range of benefits. The paper also shows how, despite being more difficult to augment with non-symbolic technologies, hybrid methods predominantly using rule-extraction techniques have provided moderate success for explanation facilities in a range of ad-hoc applications.

[1]  Sebastian Bader,et al.  Extracting Propositional Rules from Feed-forward Neural Networks - A New Decompositional Approach , 2007, NeSy.

[2]  David McSherry,et al.  Explanation in Recommender Systems , 2005, Artificial Intelligence Review.

[3]  Ivan Chorbev,et al.  Web Based Medical Expert System with a Self Training Heuristic Rule Induction Algorithm , 2009, 2009 First International Confernce on Advances in Databases, Knowledge, and Data Applications.

[4]  R. C. Eberhart,et al.  The role of genetic algorithms in neural network query-based learning and explanation facilities , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[5]  Laurie Swinney.  The explanation facility and the explanation effect , 1995 .

[6]  Russell C. Eberhart,et al.  Designing neural network explanation facilities using genetic algorithms , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[7]  Derek G. Bridge,et al.  Choosing a reasoning style for knowledge based system: lessons from supporting a help desk , 1993, The Knowledge Engineering Review.

[8]  Mary Beth Rosson,et al.  Paradox of the active user , 1987 .

[9]  Gary Riley,et al.  Expert Systems: Principles and Programming , 2004 .

[10]  Izak Benbasat,et al.  The Use of Explanations in Knowledge-Based Systems: Cognitive Perspective and a Process-Tracing Analysis , 2000, J. Manag. Inf. Syst..

[11]  L. Richard Ye,et al.  The value of explanation in expert systems for auditing: An experimental investigation , 1995 .

[12]  Bart Baesens,et al.  Using Neural Network Rule Extraction and Decision Tables for Credit - Risk Evaluation , 2003, Manag. Sci..

[13]  Edward H. Shortliffe,et al.  Computer-based medical consultations, MYCIN , 1976 .

[14]  Hilary Johnson,et al.  Explanation facilities and interactive systems , 1993, IUI '93.

[15]  E H Shortliffe,et al.  PUFF: an expert system for interpretation of pulmonary function data. , 1982, Computers and biomedical research, an international journal.

[16]  Kary Främling,et al.  Extracting Explanations from Neural Networks , 1995 .

[17]  Padraig Cunningham,et al.  An Evaluation of the Usefulness of Case-Based Explanation , 2003, ICCBR.

[18]  Carmen Lacave,et al.  A review of explanation methods for Bayesian networks , 2002, The Knowledge Engineering Review.

[19]  John R. Anderson.  Cognitive Psychology and Its Implications , 1980 .

[20]  John Riedl,et al.  Explaining collaborative filtering recommendations , 2000, CSCW '00.

[21]  Vicky Arnold,et al.  The Differential Use and Effect of Knowledge-Based System Explanations in Novice and Expert Judgement Decisions , 2006, MIS Q..

[22]  William J. Clancey,et al.  The Epistemology of a Rule-Based Expert System - A Framework for Explanation , 1981, Artif. Intell..

[23]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[24]  Shirley Diane. Gregor,et al.  Explanations from knowledge-based systems for human learning and problem solving , 1996 .

[25]  E. Shortliffe,et al.  An analysis of physician attitudes regarding computer-based clinical consultation systems. , 1981, Computers and biomedical research, an international journal.

[26]  Thomas Roth-Berghofer,et al.  Improving understandability of semantic search explanations , 2011, Int. J. Knowl. Eng. Data Min..

[27]  D. Broadbent,et al.  Explanation and Verbalization in a Computer-Assisted Search Task , 1987 .

[28]  Nick Bassiliades,et al.  Visualizing Semantic Web proofs of defeasible logic in the DR-DEVICE system , 2011, Knowl. Based Syst..

[29]  Judith Masthoff,et al.  A Survey of Explanations in Recommender Systems , 2007, 2007 IEEE 23rd International Conference on Data Engineering Workshop.

[30]  Max Bramer,et al.  Knowledge Web: a public domain expert system delivery environment , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[31]  William R. Swartout,et al.  XPLAIN: A System for Creating and Explaining Expert Consulting Programs , 1983, Artif. Intell..

[32]  Kathleen Ellen Moffitt,et al.  An empirical test of expert system explanation facility effects on incidental learning and decision-making , 1989 .

[33]  Eric J. Johnson,et al.  The adaptive decision maker , 1993 .

[34]  Alison Cawsey,et al.  Improving the Use of Knowledge-Based Systems with Explanations , 1992 .

[35]  Andre Michael Everett.  An empirical investigation of the effect of variations in expert system explanation presentation on users' acquisition of expertise and perceptions of the system , 1994 .

[36]  Peter E.D. Love,et al.  Combining rule-based expert systems and artificial neural networks for mark-up estimation , 1999 .

[37]  J. Dhaliwal.  An experimental investigation of the use of explanations provided by knowledge-based systems , 1993 .

[38]  Frada Burstein,et al.  Decision support in an uncertain and complex world , 2007, Decis. Support Syst..

[39]  Fabien Gandon,et al.  Explanation in the Semantic Web: a survey of the state of the art , 2012 .

[40]  Shirley Gregor,et al.  Explanations from knowledge-based systems and cooperative problem solving: an empirical study , 2001, Int. J. Hum. Comput. Stud..

[41]  Lorcan Coyle,et al.  Representing Cases for CBR in XML , 2002 .

[42]  Se-Hak Chun,et al.  New knowledge extraction technique using probability for case‐based reasoning: application to medical diagnosis , 2006, Expert Syst. J. Knowl. Eng..

[43]  Izak Benbasat,et al.  Explanations From Intelligent Systems: Theoretical Foundations and Implications for Practice , 1999, MIS Q..

[44]  Yehuda Koren,et al.  Advances in Collaborative Filtering , 2011, Recommender Systems Handbook.

[45]  Edward H. Shortliffe,et al.  Adapting a Consultation System to Critique User Plans , 1983, Int. J. Man Mach. Stud..

[46]  Deborah L. McGuinness,et al.  Inference Web: Portable Explanations for the Web , 2003 .

[47]  L. Richard Ye,et al.  The Impact of Explanation Facilities in User Acceptance of Expert System Advice , 1995, MIS Q..

[48]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[49]  Robbie T. Nakatsu.  Explanatory Power of Intelligent Systems : A Research Framework , 2004 .

[50]  Keith Darlington,et al.  The Essence Of Expert Systems , 2011 .

[51]  Francesco Ricci,et al.  DieToRecs: a case-based travel advisory system. , 2006 .