报告题目：Constrained Quaternion-Variable Convex Optimization

报告人：刘洋 浙江师范大学

报告摘要：This talk proposes a quaternion-valued one-layer recurrent neural network approach to resolve constrained convex function optimization problems with quaternion variables. Leveraging the novel generalized Hamilton-real (GHR) calculus, the quaternion gradient based optimization techniques is proposed to derive the optimization algorithms in the quaternion field directly, rather than the methods of decomposing the optimization problems into the complex domain or the real domain. Via chain rules and Lyapunov theorem, rigorous analysis shows that the deliberately designed quaternion-valued one-layer recurrent neural network stabilizes the the system dynamics while thestates reach the feasible region in finite time and converges to the optimal solution of the considered constrained convex optimization problems finally. Numerical simulations verify the theoretical results.

报告人简介：刘洋，浙江师范大学数学系教授，校特聘教授。同济大学理学博士，东南大学博士后，获上海市优秀博士学位论文奖。2014-2015获CSC资助访问普渡大学。近年来主要研究兴趣为系统控制理论。已经在SIAM J、Automatica、IEEE TAC、中国科学（中/英）等国内外期刊发表论文多篇。入选浙江省高校中青年学科带头人，浙江省151人才工程。担任Spring出版社出版期刊Neural Processing Letters编委（SCI），数学评论评论员。主持国家自然科学基金面上项目1项，完成国家自然科学基金项目2项，浙江省自然科学基金项目2项。

报告邀请人：李晓迪

报告时间：2019年11月26日(周二) 09:00

报告地点：长清湖校区文渊楼B区525

欢迎各位老师和同学参加！