Abductive Inference Models for Diagnostic Problem-Solving

1. Front Matter

   Pages i-xii

   PDF

2. Abduction and Diagnostic Inference

   • Yun Peng, James A. Reggia

   Pages 1-10

3. Computational Models for Diagnostic Problem Solving

   • Yun Peng, James A. Reggia

   Pages 11-47

4. Basics of Parsimonious Covering Theory

   • Yun Peng, James A. Reggia

   Pages 49-98

5. Probabilistic Causal Model

   • Yun Peng, James A. Reggia

   Pages 99-147

6. Diagnostic Strategies in the Probabilistic Causal Model

   • Yun Peng, James A. Reggia

   Pages 149-199

7. Causal Chaining

   • Yun Peng, James A. Reggia

   Pages 201-226

8. Parallel Processing for Diagnostic Problem-Solving

   • Yun Peng, James A. Reggia

   Pages 227-253

9. Conclusion

   • Yun Peng, James A. Reggia

   Pages 255-268

10. Back Matter

    Pages 269-285

    PDF

Making a diagnosis when something goes wrong with a natural or m- made system can be difficult. In many fields, such as medicine or electr- ics, a long training period and apprenticeship are required to become a skilled diagnostician. During this time a novice diagnostician is asked to assimilate a large amount of knowledge about the class of systems to be diagnosed. In contrast, the novice is not really taught how to reason with this knowledge in arriving at a conclusion or a diagnosis, except perhaps implicitly through ease examples. This would seem to indicate that many of the essential aspects of diagnostic reasoning are a type of intuiti- based, common sense reasoning. More precisely, diagnostic reasoning can be classified as a type of inf- ence known as abductive reasoning or abduction. Abduction is defined to be a process of generating a plausible explanation for a given set of obs- vations or facts. Although mentioned in Aristotle's work, the study of f- mal aspects of abduction did not really start until about a century ago.

• algorithms
• artificial intelligence
• classification
• cognitive science
• intelligence
• neural network
• problem solving
• search algorithm

• Department of Computer Science, University of Maryland, College Park, USA

  Yun Peng, James A. Reggia

• The Institute of Software, Academia Sinica, Beijing, China

  Yun Peng

Policies and ethics