Neural network that embeds its own metal-levels

Research output: Chapter in Book/Report/Conference proceedingConference contribution

53 Scopus citations


A novel recurrent neural network is presented which (in principle) can, besides learning to solve problems posed by the environment, also use its own weights as input data and learn new (arbitrarily complex) algorithms for modifying its own weights in response to the environmental input and evaluations. The network uses subsets of its input and output units for observing its own errors and for explicitly analyzing and manipulating all of its own weights, including those weights responsible for analyzing and manipulating weights. This effectively embeds a chain of 'metal-networks' and 'meta-meta-...-networks' into the network itself.
Original languageEnglish (US)
Title of host publication1993 IEEE International Conference on Neural Networks
PublisherPubl by IEEEPiscataway, NJ, United States
Number of pages6
ISBN (Print)0780312007
StatePublished - Jan 1 1993
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14


Dive into the research topics of 'Neural network that embeds its own metal-levels'. Together they form a unique fingerprint.

Cite this