应缪树鑫教授邀请，兰州大学郑兵教授将来bat365官网作学术报告。
报告题目：Artificial neural network model for some matrix computation problems
报告摘要：In recent years, the artificial neural networks have been deeply studied and investigated with the rapid development of artificial intelligence. As the powerful tools, various neural network algorithms have been designed to efficiently solve many time-varying (or time-invarying) mathematical problems widely arising from robots, space system, signal processing, and automatic control field etc. due to their parallel processing nature and easy implementation in the VLSI system. The aim of this talk is to briefly introduce a gradient-based neural network (GNN, one kind of RNN) for some static-matrix computation problems and another kind of recurrent neural network (called Zhang or zeroing neural network, ZNN) for solving time-varying matrix computation problems. These two neural network models are usually designed as the form of systems of ordinary differential equations with the initial conditions based on the derivative of the associated error function. The design and analysis of these two neural networks can be extended to more types of mathematical problems.
报告时间：2023年02月19日10:00
报告地点：教学9号楼B区311会议室
邀 请 人：缪树鑫 教授，孟令胜 副教授
届时欢迎广大师生参与交流！
报告人简介
郑兵，兰州大学bat365在线平台官网登录教授，博士生导师。长期从事数值代数、神经网络算法的研究工作，负责承担国家自然科学基金面上项目、教育部外国专家重点项目、甘肃省自然科学基金项目等10余项。多次应邀赴美国、日本、西班牙、俄罗斯、印度以及香港、澳门等国家和地区参加学术会议并做学术报告，并先后在印度统计研究所新德里中心和美国Emory大学数学与计算机系做访问学者。迄今已在SIAM J. Matrix Anal. Appl., J. Math. Anal. Appl., J. Optim. Theory Appl., Linear Algebra Appl., J. Multivariate Anal., Adv. Comput. Math., IEEE Trans. Neural Network Learn. Syst.,IEEE Trans. Fuzzy Syst., Automatica等国内外著名刊物上发表论文100余篇。2005年荣获甘肃省第十二届高校青年老师成才奖。
甘肃省数学与统计学基础学科研究中心
bat365在线平台官网登录
