Hill-Climbing Theories of Learning

Abstract

Much human learning appears to be gradual and unconscious, suggesting a very limited form of search through the space of hypotheses. We propose hill climbing as a framework for such learning and consider a number of systems that learn in this manner. We focus on CLASSIT, a model of concept formation that incrementally acquires a conceptual hierarchy, and MAGGIE, a model of skill improvement that alters motor schemas in response to errors. Both models integrate the processes of learning and performance. Keywords: Artificial intelligence; Data processing; Computer models; Computer applications.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1987
Accession Number
ADA191237

Entities

People

  • John H. Gennari
  • Pat Langley
  • Wayne Iba

Organizations

  • University of California, Irvine

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Acquisition
  • Army
  • Artificial Intelligence
  • Behavior And Behavior Mechanisms
  • Computer Science
  • Computers
  • Concept Formation
  • Coordinate Systems
  • Grammars
  • Joints (Anatomy)
  • Language
  • Machine Learning
  • Motor Skills
  • Neural Networks
  • New York
  • Psychology
  • Social Sciences

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Artificial Intelligence

Technology Areas

  • AI & ML
  • Space