报告题目：Learning Control:Ideas and Problems in Adaptive Fuzzy Control
报告时间： 2018年10月21下午2：30
报告地点： J11-118 泰山报告厅
报告人简历： 苏顺丰教授于1983年在国立台湾大学电机工程系取得学士学位，并于1989年和1991年在美国普渡大学电气工程系分别取得硕士和博士学位。现任国立台湾科技大学电机工程系的讲座教授，IEEE Fellow和CACS fellow。在国内外重要学术期刊会议发表论文300余，涉及的领域包括机器人学，智能控制，模糊系统，神经网络，无导数优化等。目前的研究领域主要包括计算智能，机器学习，虚拟现实仿真，智能交通系统，智能家居，机器人学和智能控制等。
报告摘要：Intelligent control is a promising way of control design in recent decades. Intelligent control design usually needs some knowledge of the system considered. However, such knowledge usually may not be available. Learning becomes an important mechanism for acquiring such knowledge. Learning control seems a good idea for control design for unknown or uncertain systems. To learn controllers is always a good idea, but somehow like a dream. It is because learning is to learn from something. But when there is no good controller, where to learn from? Nevertheless, there still exist approaches, such as adaptive fuzzy control, that can facilitate such an idea. It is called performance based learning (reinforcement learning and Lyapunov stability). This talk is to discuss fundamental ideas and problems in one learning controller -- adaptive fuzzy control. Some deficits of such an approach are discussed. The idea is simple and can be extended to various learning mechanisms. In fact, such an idea can also be employed in various learning control schemes. If you want to use such kind of approaches, those issues must be considered in your study.