High Performance Computing. ISC High Performance 2022 International Workshops - Hamburg, Germany, May 29 - June 2, 2022, Revised Selected Papers
High Performance Computing. ISC High Performance 2022 International Workshops - Hamburg, Germany, May 29 - June 2, 2022, Revised Selected Papers
复制标题
高性能计算。
DOI：
10.1007/978-3-031-23220-6_4
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Thiyagalingam J
中科院分区：
文献类型：
--
作者：
Thiyagalingam J
随着机器学习(ML)成为科学的变革性工具，科学界需要一个明确的ML技术目录，以及它们在各种科学问题上的相对好处，如果它们要使用人工智能在科学上取得重大进展的话。虽然这属于基准测试的范畴，但传统的基准测试倡议关注的是性能，因此，科学往往成为次要标准。在本文中，我们描述了一个工作组，即MLCommons Science Working Group，在为国际科学界开发特定于科学的人工智能基准测试方面所做的努力。自2020年工作组成立以来，该小组与世界各地的多个国家实验室、学术机构和行业非常合作，并开发了四个科学专用的人工智能基准。我们将描述整个过程、由此产生的基准以及一些初步结果。我们预计，这一倡议可能会对AI for Science和注重绩效的社区产生非常大的变革。
With machine learning (ML) becoming a transformative tool for science, the scientific community needs a clear catalogue of ML techniques, and their relative benefits on various scientific problems, if they were to make significant advances in science using AI. Although this comes under the purview of benchmarking, conventional benchmarking initiatives are focused on performance, and as such, science, often becomes a secondary criteria.In this paper, we describe a community effort from a working group, namely, MLCommons Science Working Group, in developing science-specific AI benchmarking for the international scientific community. Since the inception of the working group in 2020, the group has worked very collaboratively with a number of national laboratories, academic institutions and industries, across the world, and has developed four science-specific AI benchmarks. We will describe the overall process, the resulting benchmarks along with some initial results. We foresee that this initiative is likely to be very transformative for the AI for Science, and for performance-focused communities.