从物理视角解析深度学习训练与泛化特性，揭示其反直觉机制。
Statistical Properties of Training & Generalization
- 基于物理启发视角分析深度学习关键特性
- 揭示神经网络缩放定律与归纳偏置的相互作用
- 适合关注机器学习理论与物理建模交叉的研究者
深度学习在诸多现实任务中取得了前所未有的性能，却规避了经典统计学的诸多直觉。本文从物理启发视角探究深度学习的核心特征与意外现象，特别关注构建深度学习模型时诸多选择的内在依据。我们回顾了神经网络缩放定律，并讨论其在物理问题中的应用时，可能存在的约束与归纳偏置之间的相互作用。
原文摘要 · Abstract (English)
Deep learning has managed to evade numerous intuitions from classical statistics to achieve unprecedented performance on a number of real-world tasks. In this article, we investigate the key features and surprises of deep learning from a physics-informed perspective, taking care to point out and justify where possible the many choices inherent in constructing a deep learning model. In particular, we review the phenomenon of neural scaling laws and discuss their interplay with the constraints and inductive biases which may be present when applying machine learning to problems in physics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。