报告题目：Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems

报告时间：2022-12-07  15:00 - 16:00

报告人：蔡永强  北京师范大学

腾讯会议ID：564-388-576

Abstract：Deep learning has made significant in the fields of data science and natural science. Some studies have linked deep neural networks to dynamical systems, but the network structure is restricted to a residual network. It is known that residual networks can be regarded as a numerical discretization of dynamical systems. In this talk, we will show that vanilla feedforward networks can also be used for the numerical discretization of dynamical systems, where the width of the network is equal to the dimensions of the input and output. The proof is based on the properties of the leaky-ReLU function and the numerical technique of the splitting method for solving differential equations.