Deep Learning and Stochastic Mean-Field Control for a Neural Network Model

N. Agram, Azzeddine Bakdi, B. Øksendal
{"title":"Deep Learning and Stochastic Mean-Field Control for a Neural Network Model","authors":"N. Agram, Azzeddine Bakdi, B. Øksendal","doi":"10.2139/ssrn.3639022","DOIUrl":null,"url":null,"abstract":"We study a membrane voltage potential model by means of stochastic control of meanfield stochastic differential equations (SDEs) and by deep learning techniques. The mean-field stochastic control problem is a new type, involving the expected value of a combination of the state X(t) and the running control u(t) at time t. Moreover, the control is two-dimensional, involving both the initial value z of the state and the running control u(t). We prove a necessary condition for optimality of a control (u; z) for such a general stochastic meanfield control problem, and we also prove a verification theorem for such problems. The results are then applied to study a particular case of a neural network problem, where the system has a drift given by E[X(t)u(t)] and the problem is to arrive at a terminal state value X(T) which is close in terms of variance to a given terminal value F under minimal costs, measured by z2 and the integral of u2(t). This problem is too complicated to handle by mathematical methods alone. In the last section, we solve it using deep learning techniques.","PeriodicalId":124046,"journal":{"name":"Decision-Making in Computational Design & Technology eJournal","volume":"40 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Decision-Making in Computational Design & Technology eJournal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2139/ssrn.3639022","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

We study a membrane voltage potential model by means of stochastic control of meanfield stochastic differential equations (SDEs) and by deep learning techniques. The mean-field stochastic control problem is a new type, involving the expected value of a combination of the state X(t) and the running control u(t) at time t. Moreover, the control is two-dimensional, involving both the initial value z of the state and the running control u(t). We prove a necessary condition for optimality of a control (u; z) for such a general stochastic meanfield control problem, and we also prove a verification theorem for such problems. The results are then applied to study a particular case of a neural network problem, where the system has a drift given by E[X(t)u(t)] and the problem is to arrive at a terminal state value X(T) which is close in terms of variance to a given terminal value F under minimal costs, measured by z2 and the integral of u2(t). This problem is too complicated to handle by mathematical methods alone. In the last section, we solve it using deep learning techniques.
神经网络模型的深度学习与随机平均场控制
我们利用平均场随机微分方程(SDEs)的随机控制和深度学习技术研究膜电压电位模型。平均场随机控制问题是一种新型的随机控制问题,它涉及到状态X(t)和运行控制u(t)在时刻t的组合期望值。而且控制是二维的,既涉及到状态的初值z,也涉及到运行控制u(t)。我们证明了控制(u)最优性的一个必要条件;Z),并证明了该类问题的一个验证定理。然后将结果应用于研究神经网络问题的一个特殊情况,其中系统具有由E[X(t)u(t)]给出的漂移,问题是在最小成本下到达一个终端状态值X(t),该值在方差方面接近给定的终端值F,由z2和u2(t)的积分测量。这个问题太复杂了,单靠数学方法是处理不了的。在最后一节中,我们使用深度学习技术来解决这个问题。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书