Sign in
Comparing Huber’s M-Estimator function with the mean square error in backpropagation networks when the training data is noisy
Working paper   Open access

Comparing Huber’s M-Estimator function with the mean square error in backpropagation networks when the training data is noisy

David Clark
12/2000
Handle:
https://hdl.handle.net/10523/848

Abstract

Knowledge Engineering Laboratory QA76 Computer software
In any data set there some of the data will be bad or noisy. This study identifies two types of noise and investigates the effect of each in the training data of backpropagation neural networks. It also compares the mean square error function with a more robust alternative advocated by Huber.
pdf
dp2000-19-online.pdfDownloadView
Full text Open Access

Metrics

325 File views/ downloads
984 Record Views

Details

Usage Policy