Inductive Learning For Abductive Diagnosis

A new inductive learning system, LAB (Learning for ABduction), is presented which acquires abductive rules from a set of training examples. The goal is to find a small knowledge base which, when used abductively, diagnoses the training examples correctly and generalizes well to unseen examples. This contrasts with past systems that inductively learn rules that are used deductively. Each training example is associated with potentially multiple categories (disorders), instead of one as with typical learning systems. LAB uses a simple hill-climbing algorithm to efficiently build a rule base for a set-covering abductive system. LAB has been experimentally evaluated and compared to other learning systems and an expert knowledge base in the domain of diagnosing brain damage due to stroke.

[1]  L. Shulman,et al.  Medical Problem Solving: An Analysis of Clinical Reasoning , 1978 .

[2]  John A. Swets,et al.  Effectiveness of information retrieval methods , 1969 .

[3]  G. Gorry,et al.  Clinical problem solving: a behavioral analysis. , 1978, Annals of internal medicine.

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

[5]  Nada Lavrac,et al.  The Multi-Purpose Incremental Learning System AQ15 and Its Testing Application to Three Medical Domains , 1986, AAAI.

[6]  James A. Reggia,et al.  An experimental study of criteria for hypothesis plausibility , 1991, J. Exp. Theor. Artif. Intell..

[7]  A. Rubin,et al.  The Role Of Hypothesis in Medical Diagnosis , 1975, IJCAI.

[8]  Dan Geiger,et al.  Learning Causal Trees from Dependence Information , 1990, AAAI.

[9]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[10]  Harry E. Pople,et al.  Session 6 Theorem Proving and Logic: I I ON THE MECHANIZATION OF ABDUCTIVE LOGIC , 2006 .

[11]  Paul Thagard.  Book review: Abduetive Inference Models for Diagnostic Problem Solving by Y. Peng and J. Reggia (Springer Verlag New York 1990) , 1990 .

[12]  Hwee Tou Ng.  A General Abductive System with Application to Plan Recognition andDiagnosis , 1992 .

[13]  J. Reggia,et al.  Abductive Inference Models for Diagnostic Problem-Solving , 1990, Symbolic Computation.

[14]  Casimir A. Kulikowski,et al.  Computer Systems That Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning and Expert Systems , 1990 .

[15]  A. Hasman,et al.  Probabilistic reasoning in intelligent systems: Networks of plausible inference , 1991 .

[16]  Brian C. Williams,et al.  Diagnosing Multiple Faults , 1987, Artif. Intell..

[17]  C. Peirce,et al.  Collected Papers of Charles Sanders Peirce , 1936, Nature.

[18]  Hwee Tou Ng and Raymond J. Mooney.  A First-Order Horn-Clause Abductive System and Its Use in Plan Recognition and Diagnosis , 1992 .

[19]  J. Ross Quinlan,et al.  Generating Production Rules from Decision Trees , 1987, IJCAI.

[20]  Drew McDermott,et al.  Introduction to artificial intelligence , 1986, Addison-Wesley series in computer science.

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

[22]  Gregory F. Cooper,et al.  A Bayesian Method for the Induction of Probabilistic Networks from Data , 1992 .

[23]  Dean Allemang,et al.  Computational Complexity of Hypothesis Assembly , 1987, IJCAI.

[24]  J. R. Quinlan.  Learning Logical Definitions from Relations , 1990 .

[25]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[26]  Kurt Konolige,et al.  Abduction Versus Closure in Causal Theories , 1992, Artif. Intell..

[27]  B. Chandrasekaran,et al.  A Mechanism for Forming Composite Explanatory Hypotheses , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[28]  L. Shulman,et al.  Medical problem-solving. , 2014, Journal of medical education.

[29]  Hector J. Levesque,et al.  A Knowledge-Level Account of Abduction , 1989, IJCAI.