高级检索
王磊, 刘金国. 微分万物:深度学习的启示[J]. 物理, 2021, 50(2): 69-75. DOI: 10.7693/wl20210201
引用本文: 王磊, 刘金国. 微分万物:深度学习的启示[J]. 物理, 2021, 50(2): 69-75. DOI: 10.7693/wl20210201
WANG Lei, LIU Jin-Guo. Differentiate everything: a lesson from deep learning[J]. PHYSICS, 2021, 50(2): 69-75. DOI: 10.7693/wl20210201
Citation: WANG Lei, LIU Jin-Guo. Differentiate everything: a lesson from deep learning[J]. PHYSICS, 2021, 50(2): 69-75. DOI: 10.7693/wl20210201

微分万物:深度学习的启示

Differentiate everything: a lesson from deep learning

  • 摘要: 深度学习教会了人们一种新的和计算机打交道的方式:将一些可微分的计算单元组合形成一段程序,再通过梯度优化的方法调整程序参数,使其达成期望的目标。这就是微分编程的思想。深度学习技术的快速发展为微分编程提供了趁手的工具,也计算物理开辟了一番新天地。文章介绍微分编程的基本概念,并举例说明它在建模、优化、控制、反向设计等物理问题中的应用。

     

    Abstract: Deep learning taught us a new way to play with computers: compose differentiable components into a computer program, then tune its parameters via gradient optimization until it achieves what we want. This is the key idea of differentiable programming. The rapid development of deep learning technology offers convenient tools for differentiable programming, and also opens a new frontier for computational physics. This article introduces the basic notion of differentiable programming and its physics applications including modeling, optimization, control, and inverse design.

     

/

返回文章
返回