GPU-Accelerated Rule Evaluation and Evolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shahrzad, Hormoz, Miikkulainen, Risto
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916755597688832
author Shahrzad, Hormoz
Miikkulainen, Risto
author_facet Shahrzad, Hormoz
Miikkulainen, Risto
contents This paper introduces an innovative approach to boost the efficiency and scalability of Evolutionary Rule-based machine Learning (ERL), a key technique in explainable AI. While traditional ERL systems can distribute processes across multiple CPUs, fitness evaluation of candidate rules is a bottleneck, especially with large datasets. The method proposed in this paper, AERL (Accelerated ERL) solves this problem in two ways. First, by adopting GPU-optimized rule sets through a tensorized representation within the PyTorch framework, AERL mitigates the bottleneck and accelerates fitness evaluation significantly. Second, AERL takes further advantage of the GPUs by fine-tuning the rule coefficients via back-propagation, thereby improving search space exploration. Experimental evidence confirms that AERL search is faster and more effective, thus empowering explainable artificial intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01821
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GPU-Accelerated Rule Evaluation and Evolution
Shahrzad, Hormoz
Miikkulainen, Risto
Neural and Evolutionary Computing
This paper introduces an innovative approach to boost the efficiency and scalability of Evolutionary Rule-based machine Learning (ERL), a key technique in explainable AI. While traditional ERL systems can distribute processes across multiple CPUs, fitness evaluation of candidate rules is a bottleneck, especially with large datasets. The method proposed in this paper, AERL (Accelerated ERL) solves this problem in two ways. First, by adopting GPU-optimized rule sets through a tensorized representation within the PyTorch framework, AERL mitigates the bottleneck and accelerates fitness evaluation significantly. Second, AERL takes further advantage of the GPUs by fine-tuning the rule coefficients via back-propagation, thereby improving search space exploration. Experimental evidence confirms that AERL search is faster and more effective, thus empowering explainable artificial intelligence.
title GPU-Accelerated Rule Evaluation and Evolution
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2406.01821