Influence of graphical weights’ interpretation and filtration algorithms on generalization ability of neural networks applied to digit recognitionReport as inadecuate




Influence of graphical weights’ interpretation and filtration algorithms on generalization ability of neural networks applied to digit recognition - Download this document for free, or read online. Document in PDF available to download.

Neural Computing and Applications

, Volume 21, Issue 7, pp 1783–1790

First Online: 11 November 2011Received: 09 November 2010Accepted: 22 October 2011

Abstract

In this paper, the method of the graphical interpretation of the single-layer network weights is introduced. It is shown that the network parameters can be converted to the image and their particular elements are the pixels. For this purpose, weight-to-pixel conversion formula is used. Moreover, new weights’ modification method is proposed. The weight coefficients are computed on the basis of pixel values for which image filtration algorithms are implemented. The approach is applied to the weights of three types of the models: single-layer network, two-layer backpropagation network and the hybrid network. The performance of the models is then compared on two independent data sets. By means of the experiments, it is presented that the adjustment of the weights to new values decreases test error value compared to the error obtained for initial set of weights.

KeywordsWeights Neural network Filtration Digit recognition  Download fulltext PDF



Author: Maciej Kusy - Damian Szczepanski

Source: https://link.springer.com/







Related documents