Dynamics of Neural Networks and Their Applications
Dec. 15, 2022
In this talk, a couple applications of neural networks will be presented. First, portfolio-optimization problem in financial market. Since the objective function in the portfolio optimization is nonconvex, it is naturally challenging for designing a recurrent neural network to get its optimal solutions. However, due to the pseudoconvexity of the objective function on the feasible region, a recurrent neural network with convergence is presented for portfolio optimization to ensure the optimal solutions for portfolio optimization. Then, wvriational inequalities (VIs) and related optimization problems. Projection neural network (PNN) is proposed for solving monotone variational inequalities (VIs) and related optimization problems. Considering the inertial term into first order PNNs, an inertial PNN (IPNN) is also proposed for solving VIs. Under certain conditions, the IPNN is proved to be stable, and can be applied to solve a broader class of constrained optimization problems related to VIs. This is more convenient for exploring different Karush-Kuhn-Tucker optimal solution for nonconvex optimization problems.
Tingwen Huang is a Professor at Texas A&M University at Qatar. He received his B.S. degree from Southwest Normal University (now Southwest University), China, 1990, his M.S. degree from Sichuan University, China, 1993, and his Ph.D. degree from Texas A&M University, College Station, Texas, 2002. After graduated from Texas A&M University, he worked as a Visiting Assistant Professor there. Then he joined Texas A&M University at Qatar as an Assistant Professor in August 2003, then he was promoted to Professor in 2013. Dr. Huang’s research areas include neural networks, chaotic dynamical systems, complex networks, optimization and control, smart grid. He was conferred AFS University Level Distinguished Achievement Award for Research, the highest honor bestowed to a faculty of Texas A&M University, USA, among others.
He is a Fellow of The World Academy of Sciences, Member of the European Academy of Sciences and Arts, an Academician of the International Academy for Systems and Cybernetic Sciences, a Fellow of IEEE, IAPR (International Association of Pattern Recognition).