A Survey of Deep Learning for Scientific Discovery
Maithra Raghu1,2 Eric Schmidt1,3 1 Google 2 Cornell University 3 Schmidt Futures Correspondence to
Abstract
Over the past few years, we have seen fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. At the same time, the amount of data collected in a wide array of scientific domains is dramatically increasing in both size and complexity. Taken together, this suggests many exciting opportunities for deep learning applications in scientific settings. But a significant challenge to this is simply knowing where to start. The sheer breadth and diversity of different deep learning techniques makes it difficult to determine what scientific problems might be most amenable to these methods, or which specific combination of methods might offer the most promising first approach. In this survey, we focus on addressing this central issue, providing an overview of many widely used deep learning models, spanning visual, sequential and graph structured data, associated tasks and different training methods, along with techniques to use deep learning with less data and better interpret these complex models — two central considerations for many scientific use cases. We also include overviews of the full design process, implementation tips, and
中文速览
深度学习近年来在语音、视觉、自然语言等核心任务上取得了惊人突破，与此同时科学领域积累的数据量也在急速膨胀，两者的交汇催生出巨大的应用潜力，但真正想入门的研究者往往不知道从哪里下手。这篇综述（survey）的目标就是充当一份实用导航：它系统梳理了面向视觉、序列和图结构数据的主流深度学习模型与训练方法，并重点介绍了两类对科学应用尤为关键的技术——如何在标注数据匮乏时依然训练出可用的模型（自监督、半监督学习等），以及如何解读模型的决策过程（可解释性与表征分析）。综述还覆盖了完整的设计流程、工程实现建议，并汇集了大量社区开源代码、预训练模型和教程链接，方便读者快速上手。对于希望将深度学习引入科学研究的人来说，这篇文章提供了一个少走弯路的整体路线图，其价值不仅在于技术知识的整合，更在于帮助研究者把"我该用什么方法、从哪里起步"这个最实际的问题真正想清楚。
原文 arXiv:2003.11755;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2003.11755v1