Learning temporary variable binding with dynamic links

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

1 Scopus citations

Abstract

A novel gradient-based system for processing sequential time-varying inputs and outputs is described. With the method it is possible to train a system with time-varying inputs and outputs to use its dynamic links for temporarily binding variable contents to variable names as long as it is necessary for solving a particular task. Various learning methods for nonstationary environments are derived. Two experiments with unknown time delays illustrate the approach. A by-product of this work is the demonstration that a system consisting of two feedforward networks can solve tasks that only dynamic recurrent networks were supposed to solve.
Original languageEnglish (US)
Title of host publication1991 IEEE International Joint Conference on Neural Networks - IJCNN '91
PublisherPubl by IEEEPiscataway
Pages2075-2079
Number of pages5
ISBN (Print)0780302273
DOIs
StatePublished - Jan 1 1991
Externally publishedYes

Bibliographical note

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

Fingerprint

Dive into the research topics of 'Learning temporary variable binding with dynamic links'. Together they form a unique fingerprint.

Cite this