Title :
Self-supervised adaptive networks
Author_Institution :
Image Process. Res. Section, Defence Res. Agency, Malvern, UK
fDate :
12/1/1992 12:00:00 AM
Abstract :
A scheme for training multilayer unsupervised networks is presented, in which control signals propagate downwards from the higher layers to influence the optimisation of the lower layers. Because there is no external teacher involved, this is called self-supervised training. The author demonstrates both theoretically and numerically how self-supervision emerges when a simple network built out of vector quantisers is optimised
Keywords :
neural nets; unsupervised learning; vector quantisation; adaptive networks; control signals; higher layers; layer optimisation; lower layers; multilayer unsupervised networks; neural networks; self-supervised training; vector quantisers;
Journal_Title :
Radar and Signal Processing, IEE Proceedings F
