On the Interpolation Properties of Feedforward Layered Neural Networks.

Abstract

The characterization of the interconnection weights of an L layered feedforward neural net that interpolates through a set of points is considered. A closed form expression for the last layer of weights of a net that interpolates through m sub L - 1 + 1 points is derived in terms of the points of interpolation. These weights are a function of all the weights in the preceding layers which may be chosen at random, and m sub L -1 is the number of neurons in the layer preceding the output layer. Another method for determining all the weights of a net with only two layers of weights is also presented. This method produces a transfer function that interpolates through m sub o + 1 points or less, where m sub o is the number of inputs to the net. The norm of the Jacobian matrix of the transfer function at the interpolation points is introduced as a measure of the sensitivity of the transfer function to perturbations in the inputs of the interpolation points. The points suggest that small weights are required for low sensitivity.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1990
Accession Number
ADA238035

Entities

People

  • Jorge M. Martin

Organizations

  • Naval Air Weapons Station China Lake

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Equations
  • Functions (Mathematics)
  • Identities
  • Inequalities
  • Interpolation
  • Learning
  • Military Research
  • Neural Networks
  • Notation
  • Numbers
  • Real Numbers
  • Sensitivity
  • Standards
  • Transfer Functions

Fields of Study

  • Computer science

Readers

  • Fluid Dynamics.
  • Linear Algebra
  • Neural Network Machine Learning.

Technology Areas

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