Sub gradient iterative method for neural networks training

Shcherbakova, Galyna; Krylov, Victor; Abakumov, V. N.; Brovkov, Volodymyr; Kozina, Iuliia

doi:10.1109/idaacs.2011.6072774

Cited by 2 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors have previously developed a classification method using Haar's wavelet transform (WT) and hyperbolic WT with improved noise immunity and reduced error [30,31]. In this case, the error in determining the extremum of the objective function during processing with the Haar WT can be high (due to the asymmetry of the objective function).…”

Section: Introductionmentioning

confidence: 99%

Haar Wavelet-Based Classification Method for Visual Information Processing Systems

Wang¹,

Shcherbakova

Sachenko

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Nowadays, the systems for visual information processing are significantly extending their application field. Moreover, an unsolved problem for such systems is that the classification procedure has often-conflicting requirements for performance and classification reliability. Therefore, the goal of the article is to develop the wavelet method for classifying the systems for visual information processing by evaluating the performance and informativeness of the adopted classification solutions. This method of classification uses the Haar wavelet functions with training and calculates the ranges of changes in the coefficients of the separating surfaces. The authors proposed to select the ranges of changes in these coefficients by employing the Shannon entropy formula for measuring the information content. A case study proved that such a method will significantly increase the speed of detecting the intervals of coefficient values. In addition, this enables us to justify the choice of the width of the ranges for the change of coefficients, solving the contradiction between the performance and reliability of the classifier.

show abstract

Section: Introductionmentioning

confidence: 99%