Loading [a11y]/accessibility-menu.js
An equalized error backpropagation algorithm for the on-line training of multilayer perceptrons | IEEE Journals & Magazine | IEEE Xplore

An equalized error backpropagation algorithm for the on-line training of multilayer perceptrons


Abstract:

The error backpropagation (EBP) training of a multilayer perceptron (MLP) may require a very large number of training epochs. Although the training time can usually be re...Show More

Abstract:

The error backpropagation (EBP) training of a multilayer perceptron (MLP) may require a very large number of training epochs. Although the training time can usually be reduced considerably by adopting an on-line training paradigm, it can still be excessive when large networks have to be trained on lots of data. In this paper, a new on-line training algorithm is presented. It is called equalized EBP (EEBP), and it offers improved accuracy, speed, and robustness against badly scaled inputs. A major characteristic of EEBP is its utilization of weight specific learning rates whose relative magnitudes are derived from a priori computable properties of the network and the training data.
Published in: IEEE Transactions on Neural Networks ( Volume: 13, Issue: 3, May 2002)
Page(s): 532 - 541
Date of Publication: 31 May 2002

ISSN Information:

PubMed ID: 18244454

References

References is not available for this document.