An Integrated Framework for Learning and Reasoning

Learning and reasoning are both aspects of what is considered to be intelligence. Their studies within AI have been separated historically, learning being the topic of machine learning and neural networks, and reasoning falling under classical (or symbolic) AI. However, learning and reasoning are in many ways interdependent. This paper discusses the nature of some of these interdependencies and proposes a general framework called FLARE, that combines inductive learning using prior knowledge together with reasoning in a propositional setting. Several examples that test the framework are presented, including classical induction, many important reasoning protocols and two simple expert systems.

[1]  Jude Shavlik,et al.  Refinement ofApproximate Domain Theories by Knowledge-Based Neural Networks , 1990, AAAI.

[2]  Raymond Reiter,et al.  On Interacting Defaults , 1981, IJCAI.

[3]  Gary G. Hendrix,et al.  LEARNING BY BEING TOLD: ACQUIRING KNOWLEDGE FOR INFORMATION MANAGEMENT , 1983 .

[4]  T. Martinez,et al.  An Efficient Metric for Heterogeneous Inductive Learning Applications in the Attribute-Value Language , 1995 .

[5]  Tony R. Martinez,et al.  ILA: Combining Inductive Learning with Prior Knowledge and Reasoning , 1995 .

[6]  Melissa P. Chase,et al.  On Analytical and Similarity-Based Classification , 1990, AAAI.

[7]  Tony R. Martinez,et al.  An Incremental Learning Model for Commonsense Reasoning , 1994 .

[8]  E. Shortliffe,et al.  Readings in medical artificial intelligence: the first decade , 1984 .

[9]  Ryszard S. Michalski,et al.  A theory and methodology of inductive learning , 1993 .

[10]  Kurt Konolige,et al.  Hierarchic Autoepistemic Theories for Nonmonotonic Reasoning , 1988, AAAI.

[11]  Saso Dzeroski,et al.  Learnability of Constrained Logic Programs , 1993, ECML.

[12]  Marvin Minsky,et al.  A conversation with Marvin Minsky about agents , 1994, CACM.

[13]  J. Shavlik,et al.  Re nement of Approximate Domain Theories byKnowledge-Based Neural Networks , 1990 .

[14]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[15]  R. Sun A Connectionist Model for Commonsense Reasoning Incorporating Rules and Similarities , 1992 .

[16]  H. Sacks,et al.  Readings in Medical Artificial Intelligence: The First Decade , 1985 .

[17]  Tony R. Martinez,et al.  Adaptive self-organizing logic networks , 1986 .

[18]  Jude W. Shavlik,et al.  Knowledge-Based Artificial Neural Networks , 1994, Artif. Intell..

[19]  Brian Sawyer Programming expert systems in PASCAL , 1986 .

[20]  Tony R. Martinez,et al.  Using precepts to augment training set learning , 1993, Proceedings 1993 The First New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems.

[21]  Raymond J. Mooney,et al.  Theory Refinement Combining Analytical and Empirical Methods , 1994, Artif. Intell..

[22]  John Durkin,et al.  Expert Systems , 1994 .

[23]  David L. Waltz,et al.  Toward memory-based reasoning , 1986, CACM.

[24]  Lawrence O. Hall,et al.  A Hybrid Connectionist, Symbolic Learning System , 1990, AAAI.

[25]  David Elden Leasure The model logic Z applied to Lifschitz's benchmark problems for formal nonmonotonic reasoning , 1993 .

[26]  Raymond J. Mooney,et al.  Changing the Rules: A Comprehensive Approach to Theory Refinement , 1990, AAAI.

[27]  J. McCarthy Circumscription|a Form of Nonmonotonic Reasoning , 1979 .

[28]  John McCarthy,et al.  Circumscription - A Form of Non-Monotonic Reasoning , 1980, Artif. Intell..

[29]  Ryszard S. Michalski,et al.  The Logic of Plausible Reasoning: A Core Theory , 1989, Cogn. Sci..

[30]  Allen L. Wold,et al.  The Science of Artificial Intelligence , 1984 .

[31]  Michael D. Rychener THE INSTRUCTIBLE PRODUCTION SYSTEM: A RETROSPECTIVE ANALYSIS , 1983 .

[32]  Allen Ginsberg,et al.  Theory Reduction, Theory Revision, and Retranslation , 1990, AAAI.

[33]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[34]  Alex Goodall,et al.  The guide to expert systems , 1985 .

[35]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[36]  Ramanathan V. Guha,et al.  Enabling agents to work together , 1994, CACM.