Self-Supervision in Multilayer Adaptive Networks

Abstract

We theoretically derive and numerically simulate a new phenomenon called self-supervision, in which the higher layers of a multilayer unsupervised network control the optimisation of the lower layers, even when there is no external supervising teacher present. Self-supervision is a very convenient hybrid, which combines the best properties of unsupervised and supervised network training algorithms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1991
Accession Number
ADA247474

Entities

People

  • S. P. Luttrell

Organizations

  • Royal Signals and Radar Establishment

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Coding
  • Communication Channels
  • Compression
  • Decoding
  • Distortion
  • Equations
  • Histograms
  • Image Processing
  • Integral Equations
  • Notation
  • Probability
  • Probability Distributions
  • Random Variables
  • Simulations
  • Statistics
  • Training

Fields of Study

  • Computer science

Readers

  • Military Engineering.
  • Neural Network Machine Learning.
  • Theoretical Analysis.