Missing values imputation techniques for neural networks patterns

Authors:
Thomás López-Molina;Anna Pérez-Méndez;Francklin Rivas-Echeverría
Affiliations:
Universidad de Los Andes, Facultad de Ciencias Económicas y Sociales, Escuela de Estadística, Mérida, Venezuela;Universidad de Los Andes, Facultad de Ciencias Económicas y Sociales, Escuela de Estadística, Mérida, Venezuela;Laboratorio de Sistemas Inteligentes, Mérida, Venezuela
Venue:
ICS'08 Proceedings of the 12th WSEAS international conference on Systems
Year:
2008

Citing 5
Cited 1

Statistical analysis with missing data

Statistical analysis with missing data
Applied multivariate statistical analysis

Applied multivariate statistical analysis
Multilayer feedforward networks are universal approximators

Neural Networks
Neural network design

Neural network design
Multivariate Descriptive Statistical Analysis

Multivariate Descriptive Statistical Analysis

A robust learning model for dealing with missing values in many-core architectures

ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work presents the use of statistical techniques for data imputation for its use in artificial neural networks training. The Multiple imputation techniques used are: Metric Matching, Bayesian Bootstrap and Regression-based Minimal Square imputation. It is presented an application example for illustrating the appropriate use of these techniques.