太阳成集团tyc7111cc统计与运筹系

学术报告

Solution to the General Nonlinear Filtering Problems Based on Recurrent Neural Network

陈秀琼 讲师

（中国人民大学）

报告时间： 2024年3月26日 (星期二) 下午4:00-5:00

报告地点 ：E706

报告摘要：The famous filtering problem of estimating the state of a stochastic dynamical system from noisy observations is of central importance in engineering, and high-dimensional nonlinear filtering is still a challenging problem. This problem is reduced to solving the Duncan-Mortensen-Zakai (DMZ) equation which is satisfied by the unnormalized conditional density of the state given the observation history. For general nonlinear filtering problems, we leverage on the representation ability of recurrent neural network and provide a computationally efficient and optimal framework for nonlinear filter design based on Yau-Yau algorithm and recurrent neural network.

报告人简介：陈秀琼，现任中国人民大学数学学院讲师。2014年于太阳成集团tyc7111cc获学士学位。2019年于清华大学数学科学系获得博士学位。博士后入选清华大学“水木学者”计划。主要研究方向为控制论与非线性滤波，曾在IEEE Transactions on Automatic Control和IEEE Transactions on Neural Networks and Learning Systems等国际控制领域期刊上发表论文。现主持国家自然科学基金青年基金一项。

邀请人： 罗雪