Thermodynamics-inspired explanations of artificial intelligence.

ABSTRACT: In recent years, predictive machine learning models have gained prominence across various scientific domains. However, their black-box nature necessitates establishing trust in them before accepting their predictions as accurate. One promising strategy involves employing explanation techniques that elucidate the rationale behind a model's predictions in a way that humans can understand. However, assessing the degree of human interpretability of these explanations is a nontrivial challenge. In this work, we introduce interpretation entropy as a universal solution for evaluating the human interpretability of any linear model. Using this concept and drawing inspiration from classical thermodynamics, we present Thermodynamics-inspired Explainable Representations of AI and other black-box Parad

SUBMITTER: Mehdi S 

PROVIDER: S-EPMC11385982 | biostudies-literature | 2024 Sep

REPOSITORIES: biostudies-literature