Detecting, Classifying, and Handling Contradictions in a Large, Dynamic Information Environment

Abstract

A new approach to perturbation tolerance was identified -- the Meta-Cognitive Loop (MCL) -- for responding to contradictions and other anomalies in complex settings. Further investigations with MCL included identifying architectural requirements, and applying MCL to various domains including reinforcement learning, common-sense reasoning, and a task-oriented natural-language interface system. A series of experiments empirically demonstrated the efficacy of MCL in improving the perturbation tolerance of certain machine learning techniques, including Q-learning, SARSA and Prioritized Sweeping. Formal metrics were given for measuring the complexity, dynamicity and overall difficulty of test domains, which allow for derivative measures of perturbation tolerance. A semantics was developed for Active Logic -- the underlying logic on which MCL's contradiction handling is based -- in the propositional case.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 11, 2006
Accession Number
ADA457343

Entities

People

  • Darsana Josyula
  • Donald Perlis
  • Michael Anderson
  • Scott Fults
  • Waiyian Chong

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Cognition
  • Cognitive Science
  • Cognitive Systems Engineering
  • Computational Science
  • Computer Languages
  • Computer Science
  • Environment
  • Intelligent Agents
  • Language
  • Linguistics
  • Machine Learning
  • Natural Languages
  • Perturbations
  • Reasoning
  • Reinforcement Learning

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Artificial Intelligence
  • Groundwater Contamination Remediation.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks