Current page: Information->Indexed and Annotated Bibliography
S. Raudys
ABSTRACT
Nonrandom initial values of the weight vector can contain useful information. A weighted combination of the initial and final values of the weight vector can help to utilise this information. In adaptive training, at a start, we need to scale the initial weights and to stop training earlier before a minimum of the cost function is obtained. In order to weight, scale or to stop training optimally one needs to know the accuracy of determination of initial and final weights 
ECVision indexed and annotated bibliography of cognitive computer vision publications
This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1
The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
Prior Weights in Adaptive Pattern ClassificationSite generated on Friday, 06 January 2006