Generic-Role Limited Shells: Explicit Control Knowledge for Learning and Tutoring.

Abstract

The focus of our AFOSR-sponsored research is knowledge acquisition and machine learning methods for second-generation expert systems that solve analysis type problems, such as data interpretation, monitoring, diagnosis and troubleshooting. In particular, we focus on improvements in the design of expert shells that allow these shells to be used as critiquing expert systems in domains that involve uncertain and incomplete information. Critiquing abilities play a major role in systems for apprenticeship learning and tutoring. This report overviews the publications from this grant, which are in five areas: (1) predicting learning speed by combining general regression analysis and VC-dimension analysis; (2) improvements in refining and inducing probabilistic representations; (3) a new problem-solving method for advanced expert shells called recursive heuristic classification; (4) apprenticeship learning methods for refining knowledge based systems; and (5) papers in the area of combining knowledge acquisition and machine learning techniques.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 27, 1996
Accession Number
ADA307590

Entities

People

  • David C. Wilkins

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Acquisition
  • Applied Computer Science
  • Apprenticeship
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Classification
  • Computer Science
  • Data Science
  • Demographic Cohorts
  • Expert Systems
  • Knowledge Based Systems
  • Learning
  • Machine Learning
  • Refining
  • Regression Analysis

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks