Neuron Requirements for Classification

Abstract

The feed forward layered neural networks holds great promise for application to classification problems. Determination of the sizes of the layers is an important network design problem. This report treats the neuron requirement question from the geometric viewpoint. Threshold neurons correspond to cutting planes in the Euclidean space of input patterns. Bounds on the minimum number of first-layer neurons are determined as functions of the partition sizes of the training data sets. Bounds are also proved for convex pattern classes. Measures of separability of the training data are defined in order to emphasize the dependence of the design parameters upon the geometry of the classes.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1991
Accession Number
ADA238003

Entities

People

  • W. O. Alltop

Organizations

  • Naval Air Weapons Station China Lake

Tags

Communities of Interest

  • C4I
  • Materials and Manufacturing Processes
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Classification
  • Computer Science
  • Computing Devices
  • Convex Sets
  • Data Analysis
  • Data Sets
  • Dimensionality Reduction
  • Geometry
  • Machine Learning
  • Neural Networks
  • Pattern Recognition
  • Signal Processing
  • Theoretical Computer Science
  • Transfer Functions
  • Two Dimensional
  • Vector Spaces

Readers

  • Calculus or Mathematical Analysis
  • Neuroscience
  • Regression Analysis.

Technology Areas

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