報(bào)告人: 蘇順豐 教授 (IEEE/CACS Fellow)
邀請(qǐng)人: 史豪斌 副教授
時(shí)間: 2017年11月4日，上午10：30
地點(diǎn): 計(jì)算機(jī)學(xué)院105報(bào)告廳
主題：Learning Control: Ideas and Problems in Adaptive Fuzzy Control
內(nèi)容簡(jiǎn)介：
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 a 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. 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.
報(bào)告人簡(jiǎn)介：
蘇順豐教授1991年獲普渡大學(xué)博士學(xué)位，現(xiàn)為臺(tái)灣科技大學(xué)電子工程系講座教授，是IEEE Fellow和CACS Fellow，在機(jī)器人、智能控制、模糊系統(tǒng)、神經(jīng)網(wǎng)絡(luò)等領(lǐng)域發(fā)表論文200余篇。目前的研究興趣為計(jì)算智能、機(jī)器學(xué)習(xí)、智能交通系統(tǒng)等。他是國(guó)際模糊系統(tǒng)協(xié)會(huì)的前任主席，IEEE Systems, Man, and Cybernetics Society的理事會(huì)成員，擔(dān)任過(guò)多個(gè)國(guó)際會(huì)議的大會(huì)主席或程序委員會(huì)主席，現(xiàn)為IEEE Transactions on Cybernetics、IEEE Transactions on Fuzzy Systems、IEEE Access的編委以及International Journal of Fuzzy Systems主編。
