非光滑极小极大神经网络收敛性分析

Convergence Analysis for Nonsmooth Minimax Neural Networks

利用非光滑分析的理论讨论了非可微鞍泛函的ｍｉｎｉｍａｘ问题，并建立非光滑神经网络来求鞍泛函的鞍点。在适当的条件下。

This paper investigates the minimax problem of a non differentiable saddle functional,and constructs a nonsmooth neural network to search for the saddle point of a saddle functional.Under suitable conditions the convergence and stability of the network are discussed,using Lyapunov theory.