The Open Cybernetics & Systemics Journal
2007, 1 : 1-4Published online 2007 August 7. DOI: 10.2174/1874110X00701010001
Publisher ID: TOCSJ-1-1
Theoretical Analysis of Cross-Correlation of Time-Series Signals Computed by a Time-Delayed Hebbian Associative Learning Neural Network
Department of Biological
Sciences, University of North Texas, Denton, Texas 76203, USA.
ABSTRACT
A theoretical proof of the computational function performed by a time-delayed neural network implementing a Hebbian associative learning-rule is shown to compute the equivalent of cross-correlation of time-series functions, showing the relationship between correlation coefficients and connection-weights. The values of the computed correlation coefficients can be retrieved from the connection-weights.