Abstract HTML Views: 394 PDF Downloads: 436 Total Views/Downloads: 830
Abstract HTML Views: 249 PDF Downloads: 315 Total Views/Downloads: 564
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.