We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Thermodynamics-inspired explanations of artificial intelligence.
- Authors
Mehdi, Shams; Tiwary, Pratyush
- 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 Paradigms, a method for generating optimally human-interpretable explanations in a model-agnostic manner. We demonstrate the wide-ranging applicability of this method by explaining predictions from various black-box model architectures across diverse domains, including molecular simulations, text, and image classification. Predictive machine learning models, while powerful, are often seen as black boxes. Here, the authors introduce a thermodynamics-inspired approach for generating rationale behind their explanations across diverse domains based on the proposed concept of interpretation entropy.
- Subjects
MACHINE learning; IMAGE recognition (Computer vision); ARTIFICIAL intelligence; ENTROPY; THERMODYNAMICS
- Publication
Nature Communications, 2024, Vol 15, Issue 1, p1
- ISSN
2041-1723
- Publication type
Article
- DOI
10.1038/s41467-024-51970-x