Designing the Architecture of Hierachical Neural Networks Model Attention, Learning and Goal-Oriented Behavior

Abstract

During this period this grant partially supported 6 researchers, and resulted in over 21 publications. This unusually large activity is largely due to the enthusiasm of the researchers and their institution, Drexel University, which indirectly carried some of the financial burden. Neural or other learning architecture for real world, real time applications, necessarily employ feedback and thus deal with the unavoidable dilemma of identification versus stabilization or tracking. The major finding reported focuses on this tradeoff and how to optimally perform it. For linear time invariant finite dimensional systems they are able to perform on-line closed loop identification and tracking. If in addition the learning and tracking cost functions are quadratic they show these costs may be linearly scalarized without loss of optimality.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 31, 1993
Accession Number
ADA279898

Entities

People

  • Allon Guez

Organizations

  • Drexel University

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Ground and Sea Platforms
  • Weapons Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Aircrafts
  • Algorithms
  • Computational Science
  • Control Systems
  • Feedback
  • Identification
  • Information Systems
  • Learning
  • Linear Systems
  • Machine Learning
  • Mathematical Models
  • Multiobjective Optimization
  • Neural Networks
  • Pattern Recognition
  • Recognition
  • Target Classification

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Educational Psychology
  • Research Science/Academic Research

Technology Areas

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