Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

三分钟入门DeepONet

less than 1 minute read

Published:

神经网络可以作为通用的函数逼近器。但是还有一个古老的理论——Universal Approximation Theorem for Operator(Chen et al. 1995)表示,神经网络可以被用来逼近数学算子(比如积分,常微分方程ODEs,偏微分方程PDEs),实现函数到函数/实数的映射。为了方便讨论,我们用$G$来表示要拟合的算子,$G(u)(y)$则是经过算子操作得到的新函数在$y$处的值。比如,$G$可以表示对函数$u(x)$做不定积分,$G: u(x) →s(x)=\int_0^xu(\tau)d\tau$。

portfolio

publications

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.