Learning multiple-input operators via tensor product
组织者
演讲者
时间
2023年10月27日 20:30 至 21:00
地点
Online
摘要
In this talk, we will share a work about the neural operator. Basically, neural operators aim to learn operators, via neural networks, that map between infinite-dimensional function spaces. So far, all the existing neural operators are only designed to learn operators defined on a single Banach space. In the presented paper from Jin et al, multiple-input operators are considered called MIONet which can deal with multiple input problems.
演讲者介绍
焦小沛,本科毕业于上海交通大学致远学院,博士毕业于清华大学数学科学系。先后在北京雁栖湖应用数学研究院,荷兰特文特大学从事博士后工作。现研究方向包括有限维滤波理论,丘-丘滤波方法,物理信息神经网络以及生物信息学。研究兴趣主要集中于(1)利用李代数等几何工具进行偏微分方程求解与有限维滤波系统的分类;(2)设计基于物理信息神经网络的新型数值算法。