arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.10019astro-ph.IMastro-ph.GAastro-ph.HEcs.AIcs.LGphysics.data-an
收藏

AI能理解我们的宇宙吗?利用天体物理数据微调GPT的测试

Can AI Understand Our Universe? Test of Fine-Tuning GPT by Astrophysical Data

International Center for Relativistic Astrophysics (ICRA)(国际相对论天体物理中心);International Center for Relativistic Astrophysics Network (ICRANet)(国际相对论天体物理网络中心);University of Science and Technology of China(中国科学技术大学);University of Padova(帕多瓦大学);Institute of High Energy Physics, Chinese Academy of Sciences(中国科学院高能物理研究所);ICRANet-Armenia(国际相对论天体物理网络中心亚美尼亚分部);Isfahan University of Technology(伊斯法罕理工大学)

Yu Wang, Shu-Rui Zhang, Aidin Momtaz, Rahim Moradi, Fatemeh Rastegarnia, Narek Sahakyan, Soroush Shakeri, Liang Li

AI总结:

本文用星系、类星体、恒星、GRB观测及黑洞模拟数据微调GPT,验证其分类、红移推断和参数估计等天体物理分析能力,并探讨AI设计方法。

摘要:

近几个月来,ChatGPT一直是最受热议的概念,吸引了专业人士和普通公众的关注,并引发了关于人工智能(AI)将给世界带来何种变革的讨论。作为物理学家和天体物理学家,我们好奇的是,大语言模型(LLM)能否正确分析科学数据并得出准确的物理结果。在本文中,我们利用来自星系、类星体、恒星、伽马射线暴(GRB)观测以及黑洞(BH)模拟的天文数据,对生成式预训练Transformer(GPT)模型进行微调;微调后的模型展示出其对天体物理现象进行分类、区分两类GRB、推断类星体红移以及估计BH参数的能力。我们将此视为一次成功的测试,标志着LLM在科学研究中的有效性得到验证。随着多学科数据量的不断增长以及AI技术的进步,我们期待出现对宇宙更根本、更全面的理解。本文还分享了关于数据收集和AI设计的一些有趣思考。以理解宇宙的方法——向外审视数据、向内寻找基本构建单元——为指导,我们提出了一种用于AI的级数展开方法,为训练和控制比人类更聪明的AI给出了建议。

英文摘要:

ChatGPT has been the most talked-about concept in recent months, captivating both professionals and the general public alike, and has sparked discussions about the changes that artificial intelligence (AI) will bring to the world. As physicists and astrophysicists, we are curious about if scientific data can be correctly analyzed by large language models (LLMs) and yield accurate physics. In this article, we fine-tune the generative pre-trained transformer (GPT) model by the astronomical data from the observations of galaxies, quasars, stars, gamma-ray bursts (GRBs), and the simulations of black holes (BHs), the fine-tuned model demonstrates its capability to classify astrophysical phenomena, distinguish between two types of GRBs, deduce the redshift of quasars, and estimate BH parameters. We regard this as a successful test, marking the LLM's proven efficacy in scientific research. With the ever-growing volume of multidisciplinary data and the advancement of AI technology, we look forward to the emergence of a more fundamental and comprehensive understanding of our universe. This article also shares some interesting thoughts on data collection and AI design. Using the approach of understanding the universe - looking outward at data and inward for fundamental building blocks - as a guideline, we propose a method of series expansion for AI, suggesting ways to train and control AI that is smarter than humans.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑