EVOTER: Evolution of Transparent Explainable Rule-sets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shahrzad, Hormoz, Hodjat, Babak, Miikkulainen, Risto
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917814732849152
author Shahrzad, Hormoz
Hodjat, Babak
Miikkulainen, Risto
author_facet Shahrzad, Hormoz
Hodjat, Babak
Miikkulainen, Risto
contents Most AI systems are black boxes generating reasonable outputs for given inputs. Some domains, however, have explainability and trustworthiness requirements that cannot be directly met by these approaches. Various methods have therefore been developed to interpret black-box models after training. This paper advocates an alternative approach where the models are transparent and explainable to begin with. This approach, EVOTER, evolves rule-sets based on simple logical expressions. The approach is evaluated in several prediction/classification and prescription/policy search domains with and without a surrogate. It is shown to discover meaningful rule sets that perform similarly to black-box models. The rules can provide insight into the domain, and make biases hidden in the data explicit. It may also be possible to edit them directly to remove biases and add constraints. EVOTER thus forms a promising foundation for building trustworthy AI systems for real-world applications in the future.
format Preprint
id arxiv_https___arxiv_org_abs_2204_10438
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle EVOTER: Evolution of Transparent Explainable Rule-sets
Shahrzad, Hormoz
Hodjat, Babak
Miikkulainen, Risto
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
Most AI systems are black boxes generating reasonable outputs for given inputs. Some domains, however, have explainability and trustworthiness requirements that cannot be directly met by these approaches. Various methods have therefore been developed to interpret black-box models after training. This paper advocates an alternative approach where the models are transparent and explainable to begin with. This approach, EVOTER, evolves rule-sets based on simple logical expressions. The approach is evaluated in several prediction/classification and prescription/policy search domains with and without a surrogate. It is shown to discover meaningful rule sets that perform similarly to black-box models. The rules can provide insight into the domain, and make biases hidden in the data explicit. It may also be possible to edit them directly to remove biases and add constraints. EVOTER thus forms a promising foundation for building trustworthy AI systems for real-world applications in the future.
title EVOTER: Evolution of Transparent Explainable Rule-sets
topic Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2204.10438