Madaline Rule II: An Investigation

Abstract

Madaline Rule II, MRII, is a supervised learning algorithm for training layered feed forward networks of Adalines. An Adaline is a basic neuron-like processing element which forms a binary output based upon a weighted sum of its inputs. The algorithm was developed based on the minimal disturbance principle. This principle states that changes made to the network to correct errors should disturb it as little as possible. A method to insure all processing elements share responsibility for forming the global solution was introduced and called usage. Details of the algorithm were developed with consideration for hardware implementation. (emk)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1989
Accession Number
ADA217839

Entities

People

  • Rodney G. Winter

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • C4I
  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Algorithms
  • Computational Science
  • Computers
  • Content Addressable Memory
  • Detectors
  • Failure Mode And Effect Analysis
  • Geometry
  • Layers
  • Logic Elements
  • Mathematical Analysis
  • Neural Networks
  • Pattern Recognition
  • Plane Geometry
  • Probability
  • Simulations
  • Three Dimensional

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Software Engineering

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks