Semantic Scholar Open Access 2022 285 sitasi

Explainable machine learning in materials science

Xiaoting Zhong Brian Gallagher Shusen Liu B. Kailkhura A. Hiszpanski +1 lainnya

Lihat Sumber DOI

Abstrak

Machine learning models are increasingly used in materials studies because of their exceptional accuracy. However, the most accurate machine learning models are usually difficult to explain. Remedies to this problem lie in explainable artificial intelligence (XAI), an emerging research field that addresses the explainability of complicated machine learning models like deep neural networks (DNNs). This article attempts to provide an entry point to XAI for materials scientists. Concepts are defined to clarify what explain means in the context of materials science. Example works are reviewed to show how XAI helps materials science research. Challenges and opportunities are also discussed.

Penulis (6)

Xiaoting Zhong

Brian Gallagher

Shusen Liu

B. Kailkhura

A. Hiszpanski

T. Y. Han

Format Sitasi

APA MLA BibTeX

Zhong, X., Gallagher, B., Liu, S., Kailkhura, B., Hiszpanski, A., Han, T.Y. (2022). Explainable machine learning in materials science. https://doi.org/10.1038/s41524-022-00884-7

Akses Cepat

Lihat di Sumber doi.org/10.1038/s41524-022-00884-7

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Total Sitasi: 285×
Sumber Database: Semantic Scholar
DOI: 10.1038/s41524-022-00884-7
Akses: Open Access ✓