Data are the core of deep learning (DL), and the quality of data significantly affects the performance of DL models. However, high-quality and well-annotated databases are hard or even impossible to acquire for use in many applications, such as structural risk estimation and medical diagnosis, which is an essential barrier that blocks the applications of DL in real life. Physics-guided deep learning (PGDL) is a novel type of DL that can integrate physics laws to train neural networks. It can be used for any systems that are controlled or governed by physics laws, such as mechanics, finance and medical applications. It has been shown that, with the additional information provided by physics laws, PGDL achieves great accuracy and generalisation when facing data scarcity. In this review, the details of PGDL are elucidated, and a structured overview of PGDL with respect to data scarcity in various applications is presented, including physics, engineering and medical applications. Moreover, the limitations and opportunities for current PGDL in terms of data scarcity are identified, and the future outlook for PGDL is discussed in depth.
翻译:数据是深层次学习的核心,数据的质量对高层次和注解良好的数据模型的性能有重大影响,然而,高质量的、有详细说明的数据库很难或甚至不可能获得,供许多应用软件使用,例如结构风险估计和医学诊断,这是阻碍DL在现实生活中应用的基本障碍。物理引导深层次学习(PGDL)是一种新型的DL,可以将物理法纳入神经网络的培训;可用于受物理法控制或规范的任何系统,例如机械、财政和医疗应用;已经表明,随着物理法提供的额外信息,PGDL在面临数据稀缺时,非常准确和概括。在这次审查中,对PGDL的细节进行了阐述,并介绍了PGDL在包括物理、工程和医疗应用在内的各种应用中数据稀缺方面的结构化概况。此外,还查明了目前PGDL在数据稀缺方面的局限性和机会,并深入讨论了PGDL的未来前景。