Unified approach to learning for complex real-world domains

This paper presents the unified approach to machine learning and knowledge acquisition in the Case-Oriented Expert (COEx) system architecture. Knowledge acquisition techniques are used to delineate a problem class hierarchy for complex real-world planning tasks. This hierarchy is stepwise formalized into a KL-ONE-like representation. Explanation-based abstraction is then applied to previously solved cases, and procedure schemata are constructed for the different problem classes. COEx is a type of apprenticeship learning system where reversed engineering is applied to success cases from the real world. An evaluation of this unification reveals its conceptual soundness and several technical problems.

[1]  Paul J. Feltovich,et al.  Categorization and Representation of Physics Problems by Experts and Novices , 1981, Cogn. Sci..

[2]  Ronald J. Brachman,et al.  An overview of the KL-ONE Knowledge Representation System , 1985 .

[3]  Ralph Bergmann.  Learning Plan Abstractions , 1992, GWAI.

[4]  Nigel Shadbolt,et al.  A conceptual model of hierarchical skeletal planning and its formalization , 1993 .

[5]  Christoph Klauck.  Eine Graphgrammatik zur Repräsentation und Erkennung von Features in CAD/CAM , 1994, DISKI.

[6]  R. Bergmann.  Explanation-based learning for the automated reuse of programs , 1992, CompEuro 1992 Proceedings Computer Systems and Software Engineering.

[7]  Roger C. Schank,et al.  Where's the AI? , 1991, AI Mag..

[8]  Andreas Birk,et al.  Architecture and User Interface of the IDEAS Intelligent Documentation System , 1995, Designing User Interfaces for Hypermedia.

[9]  Thomas Ellman,et al.  Explanation-based learning: a survey of programs and perspectives , 1989, CSUR.

[10]  Ralph Bergmann,et al.  Using Integrated Knowledge Acquisition to Prepare Sophisticated Expert Plans for Their Re-Use in Novel Situations , 1991, GWAI.

[11]  Douglas H. Fisher,et al.  Knowledge Acquisition Via Incremental Conceptual Clustering , 1987, Machine Learning.

[12]  E. Morales.  The Machine Learning Toolkit Database , 1990 .

[13]  Bob Wielinga,et al.  Models of Expertise in Knowledge Acquisition , 1989 .

[14]  Franz Schmalhofer,et al.  The Model-Based Construction of a Case-Oriented Expert System , 1992, AI Commun..

[15]  Richard E. Korf,et al.  Planning as Search: A Quantitative Approach , 1987, Artif. Intell..

[16]  Franz Schmalhofer,et al.  Situated text-analysis with COKAM+ , 1991 .

[17]  Eleanor Rosch,et al.  Principles of Categorization , 1978 .

[18]  LebowitzMichael.  Experiments with Incremental Concept Formation , 1987 .

[19]  Josh D. Tenenberg.  Preserving Consistency Across Abstraction Mappings , 1987, IJCAI.

[20]  F. Schmalhofer,et al.  Chapter 10 Learning Program Abstractions: Model and Empirical Validation , 1993 .

[21]  Peter F. Patel-Schneider,et al.  Living wiht Classic: When and How to Use a KL-ONE-Like Language , 1991, Principles of Semantic Networks.

[22]  Brian R. Gaines,et al.  Knowledge acquisition for knowledge-based systems: Notes on the state-of-the-art , 1989, Machine Learning.

[23]  Gheorghe Tecuci,et al.  Techniques of design and DISCIPLE learning apprentice , 1987 .

[24]  Michael Lebowitz,et al.  Experiments with incremental concept formation: UNIMEM , 2004, Machine Learning.

[25]  Franz Schmalhofer,et al.  The Acquisition of a procedure schema from text and experiences , 1993 .

[26]  Terry Winograd,et al.  Understanding natural language , 1974 .

[27]  Andreas Abecker,et al.  TAXON: A Concept Language with Concrete Domains , 1991, PDK.

[28]  Tom M. Mitchell,et al.  A learning apprentice system for VLSI design , 1986 .

[29]  Gheorghe Tecuci,et al.  Apprenticeship learning in imperfect domain theories , 1990 .

[30]  Ryszard S. Michalski,et al.  Research in machine learning: recent progress, classification of methods, and future directions , 1990 .

[31]  Ray Bareiss,et al.  Concept Learning and Heuristic Classification in WeakTtheory Domains , 1990, Artif. Intell..

[32]  James Kelly,et al.  AutoClass: A Bayesian Classification System , 1993, ML.

[33]  Franz Baader.  Augmenting Concept Languages by Transitive Closure of Roles: An Alternative to Terminological Cycles , 1991, IJCAI.

[34]  H. Boley,et al.  Konzeption einer deklarativen Wissensbasis über recyclingrelevante Materialien , 1993 .

[35]  David A. Plaisted,et al.  Theorem Proving with Abstraction , 1981, Artif. Intell..

[36]  Gabriele Schmidt.  Knowledge Acquisition from Text in a Complex Domain , 1992, IEA/AIE.

[37]  Franz Baader,et al.  A Scheme for Integrating Concrete Domains into Concept Languages , 1991, IJCAI.

[38]  Craig A. Knoblock.  Learning Abstraction Hierarchies for Problem Solving , 1990, AAAI.

[39]  Ralph Bergmann,et al.  Learning program abstractions: Formal model and empirical validation , 1993 .

[40]  Otto Kühn,et al.  Conserving corporate knowledge for crankshaft design , 1994, IEA/AIE '94.

[41]  Franz Schmalhofer,et al.  Hierarchical skeletal plan refinement : task- and inference structures , 1992 .