A Novel Target Value Standardization Method Based on Cumulative Distribution Functions for Training Artificial Neural Networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Function approximation by artificial neural networks (ANNs) are often carried out via a collocation grid approach. However, for certain combinations of grids and functions, the training data for the relevant ANN can be extremely skewed and hence affect training efficiency, thereby necessitating standardization or normalization techniques. The choice of collocation grids often allows uniform training features but not targets. In this paper, we contribute a comparison between methods of target standardization - the relatively common min-max, z score, normalized log methods and the uncommon empirical cumulative distribution function (CDF) method - in terms of the resulting approximation capabilities of the ANNs using the standardized target values. We demonstrate that the empirical CDF is a general and robust standardization method that allows for efficient training and good approximations insituations of extreme target skewness. Novel modifications using a mix of true CDF and empirical CDF in standardizing targets are used to successfully reduce biases arising from the empirical CDF standardization method.
Original languageEnglish
Title of host publication13th IEEE Symposium on Computer Applications & Industrial Electronics 2023
PublisherIEEE
Pages250-255
Number of pages6
ISBN (Electronic)9798350347319
DOIs
Publication statusPublished - 3 Jul 2023
Event13th IEEE Symposium on Computer Applications & Industrial Electronics 2023 - Penang, Malaysia
Duration: 20 May 202321 May 2023

Conference

Conference13th IEEE Symposium on Computer Applications & Industrial Electronics 2023
Abbreviated titleISCAIE 2023
Country/TerritoryMalaysia
CityPenang
Period20/05/2321/05/23

Keywords

  • Artificial Neural Networks
  • Cumulative Distribution Functions
  • Forward Problems
  • Function Approximation
  • Machine Learning
  • Target Standardization

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Information Systems and Management
  • Statistics, Probability and Uncertainty
  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Instrumentation

Fingerprint

Dive into the research topics of 'A Novel Target Value Standardization Method Based on Cumulative Distribution Functions for Training Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this