Mathematical Methods for the Implementation of Neural Networks.

Abstract

We present a novel optimizing network architecture with applications in vision, learning, pattern recognition and combinatorial optimization. This architecture is constructed by combining the following techniques: (1) deterministic annealing, (2) self-amplification, (3) algebraic transformations, (4) clocked objectives, and (5) soft assign. Deterministic annealing in conjunction with self-amplification avoids poor local minima and ensures that a vertex of the hypercube is reached. Algebraic transformations and clocked objectives help partition the relaxation into distinct phases. The problems considered have doubly stochastic matrix constraints or minor variations thereof. We introduce a new technique, soft assign, which is used to satisfy this constraint. Experimental results on different problems are presented and discussed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 18, 1996
Accession Number
ADA336777

Entities

People

  • Eric Mjolsness

Organizations

  • Yale University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Applied Computer Science
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Computer Science
  • Computer Vision
  • Computers
  • Dynamics
  • Learning
  • Machine Learning
  • Mathematical Programming
  • Neural Networks
  • Optimization

Fields of Study

  • Computer science

Readers

  • Operations Research

Technology Areas

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