Introduction to Relational Networks for Classification

TL;DR

This paper introduces Relational Networks for classification, comparing their architecture and performance to neural networks in HIV status prediction, showing comparable accuracy and revealing feature relationships.

Contribution

It presents a new Relational Network architecture and evaluates its effectiveness against neural networks for HIV classification tasks.

Findings

Relational Networks achieve comparable accuracy to neural networks.

The study reveals relationships between data features in HIV classification.

Results suggest potential for improved future classification accuracy.

Abstract

The use of computational intelligence techniques for classification has been used in numerous applications. This paper compares the use of a Multi Layer Perceptron Neural Network and a new Relational Network on classifying the HIV status of women at ante-natal clinics. The paper discusses the architecture of the relational network and its merits compared to a neural network and most other computational intelligence classifiers. Results gathered from the study indicate comparable classification accuracies as well as revealed relationships between data features in the classification data. Much higher classification accuracies are recommended for future research in the area of HIV classification as well as missing data estimation.