BIMSA > BIMSA 计算数学讨论班 BIMSA 计算数学讨论班 A Unified Neural Flow Framework for Neural Networks and Operators
A Unified Neural Flow Framework for Neural Networks and Operators
组织者
塔赫蕾·埃夫特哈里 , 胡丕丕 , 梁鑫 , 马志婷 , 哈米德·莫菲迪 , 苏春梅 , Axel G.R. Turnquist , 王丽 , 熊繁升 , 杨朔 , 杨武岳
演讲者
何俊材
时间
2026年05月13日 14:00 至 15:00
地点
A3-4-312
线上
Zoom 518 868 7656 (BIMSA)
摘要
In this talk, we introduce a unified neural flow framework that provides an infinite-depth formulation for deep neural networks and operators. Two representative dynamical systems recover plain and ResNet-type architectures through time discretization. We establish well-posedness and develop approximation theory for both networks and operators. The framework also incorporates various spatial discretizations for inter-neuron linear operators, enabling coverage of existing neural operator architectures and yielding approximation results for finite-depth DNNs, CNNs, and neural operators within a single continuous perspective.