EVOTER: Evolution of Transparent Explainable Rule-sets

arXiv:2204.10438v4 Announce Type: replace-cross
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 …

abstract ai systems arxiv black boxes box cs.ai cs.lg cs.ne domains evolution explainability however inputs paper requirements systems training transparent type