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.
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