Adaptive behavior with fixed weights in RNN: an overview

In this paper we review recent results on the adaptive behavior attained with fixed-weight recurrent neural networks (meta-learning). We argue that such behavior is a natural consequence of prior training.

Saved in:
Bibliographic Details
Published inProceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Vol. 3; pp. 2018 - 2022 vol.3
Main Authors Prokhorov, D.V., Feldkarnp, L.A., Tyukin, I.Yu
Format Conference Proceeding
LanguageEnglish
Published IEEE 2002
Subjects
Equations
Feedback
Intelligent networks
Multilayer perceptrons
Recurrent neural networks
Online AccessGet full text

Cover

More Information
Summary:In this paper we review recent results on the adaptive behavior attained with fixed-weight recurrent neural networks (meta-learning). We argue that such behavior is a natural consequence of prior training.
ISBN:0780372786
9780780372788
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.2002.1007449