Informatics Report Series


Report   

EDI-INF-RR-0149


Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Home
Title:Correlated sequence learning in a network of spiking neurons using maximum likelihood
Authors: David Barber ; Felix Agakov
Date:Apr 2002
Publication Title:Neural Computation
Abstract:
Hopfield Networks are an idealised model of distributed computation in networks of non-linear, stochastic units. We consider the learning of correlated temporal sequences using Maximum Likelihood, deriving a simple Hebbian-like learning rule that is capable of robustly storing multiple sequences of correlated patterns. We argue that the learning rule is optimal for the case of long temporal sequences and has a natural stochastic interpretation.
Copyright:
2002 by The University of Edinburgh. All Rights Reserved
Links To Paper
No links available
Bibtex format
@Misc{EDI-INF-RR-0149,
author = { David Barber and Felix Agakov },
title = {Correlated sequence learning in a network of spiking neurons using maximum likelihood},
year = 2002,
month = {Apr},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh