Evolution of Transparent Explainable Rule-sets
Created by W.Langdon from
gp-bibliography.bib Revision:1.8098
- @Misc{shahrzad:arxiv22,
-
author = "Hormoz Shahrzad and Babak Hodjat and
Risto Miikkulainen",
-
title = "Evolution of Transparent Explainable Rule-sets",
-
howpublished = "arXiv",
-
year = "2022",
-
month = "21 " # apr,
-
keywords = "genetic algorithms, genetic programming, Artificial
Intelligence (cs.AI), Machine Learning (cs.LG), Neural
and Evolutionary Computing (cs.NE), FOS: Computer and
information sciences, FOS: Computer and information
sciences",
-
URL = "http://nn.cs.utexas.edu/?shahrzad:arxiv22",
-
URL = "https://arxiv.org/abs/2204.10438",
-
DOI = "doi:10.48550/ARXIV.2204.10438",
-
abstract = "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 to 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.",
- }
Genetic Programming entries for
Hormoz Shahrzad
Babak Hodjat
Risto Miikkulainen
Citations