End-to-End Neural Network Training for Hyperbox-Based Classification

TL;DR

This paper introduces a fully differentiable neural network framework for hyperbox-based classification, enabling efficient end-to-end training that improves speed and accuracy over traditional methods.

Contribution

It presents a novel neural network approach for hyperbox classification that allows for end-to-end training, addressing scalability and efficiency issues of prior methods.

Findings

Reduced training times compared to traditional hyperbox methods

Improved classification accuracy on benchmark datasets

Demonstrated scalability to large data volumes

Abstract

Hyperbox-based classification has been seen as a promising technique in which decisions on the data are represented as a series of orthogonal, multidimensional boxes (i.e., hyperboxes) that are often interpretable and human-readable. However, existing methods are no longer capable of efficiently handling the increasing volume of data many application domains face nowadays. We address this gap by proposing a novel, fully differentiable framework for hyperbox-based classification via neural networks. In contrast to previous work, our hyperbox models can be efficiently trained in an end-to-end fashion, which leads to significantly reduced training times and superior classification results.