【百家大讲堂】第200期:机器学习辅助的无线技术:过去、现状与未来
来源: 发布日期:2019-05-21
【百家大讲堂】第200 期:机器学习辅助的无线技术:过去、现状与未来
讲座题目:机器学习辅助的无线技术:过去、现状与未来
报 告 人:教授Lajos Hanzo
时 间:2019年5 月30日下午14:30-16:30
地 点:信息科学实验楼202报告厅
主办单位:研究生院、信息与电子学院
报名方式:登录欧洲杯足球网_欧洲杯网投-投注|官网:微信企业号---第二课堂---课程报名中选择“【百家大讲堂】第200期:机器学习辅助的无线技术:过去、现状与未来 ”
【主讲人简介】
Lajos Hanzo教授:于1983年在布达佩斯技术大学获得博士学位,于2004年在英国南安普敦大学被授予荣誉博士学位,目前是英国皇家工程院院士,电子电气工程师协会会士(IEEE Fellow),工程技术协会会士(IET Fellow),IEEE通信学会Governor,IEEE车载技术学会Governor,清华大学信息科学与技术国家实验室讲席教授,在IEEE期刊及会议上发表文章超过1700篇,著有20多本学术著作。Hanzo教授担任了多次国际学术会议总主席或技术程序委员会主席,他在2008年-2012年期间还担任了IEEE出版社主编。
主讲人简介(英文)
Lajos Hanzo received his Doctorate in 1983 from the Technical University of Budapest and was awarded the Doctor of Science degree from the University of Southampton in 2004. He is a Fellow of the Royal Academy of Engineering (FREng), FIEEE, FIET. He is a Govenor of the IEEE ComSoc and IEEE VTS. He is also a Chaired Professor at Tsinghua University. Prof. Hanzo has co-authored 20 books and published more than 1700 research papers in at IEEE Xplore. He has also organized and chaired major IEEE conferences. During 2008 to 2012, he was the Editor-in-Chief of the IEEE Press.
【讲座信息】
虽然对未来的研究方向进行预测充满着挑战性,但同时也给予了我们“未卜先知”的特权。本次报告将从更广泛的视角出发,以(A)性能指标,(B)设计和优化工具以及(C)解决方案和应用这三个不同的角度探索未来的无线技术。目前学术界的研究热点是设计基于帕累托最优的无线系统。对于一个帕累托最优系统而言,只能通过降低系统的一部分效能以改进上述提到的性能指标。为设计满足帕累托最优的系统,必须采用基于生物启发、机器学习和量子搜索辅助的优化技术,并借助多元优化算法,而这些算法具有巨大的搜索空间。接下来让我们探讨如何解决所面临的这些挑战!
内容简介(英文,如有)
It is always a challenge, but also a privilege to embark on `crystal-ball gazing', when we try and predict the directions of frontier-research beyond the horizon. So, valued Colleague, let's just just that together! Commencing on a broad note, let's adopt a light-hearted three-pronged approach, touching upon A/ the performance metrics; B/ the design and optimization tools and C/ compelling solutions/applications; Our research community is now poised to enter the era of designing Pareto-optimum systems, where - by definition - it is only possible to improve any of the above-mentioned metrics at the cost of degrading some of the others. Sophisticated bio-inspired, machine-learning and quantum-search assisted optimization techniques will have to be used for designing Pareto-optimum solutions with the aid of multi-component optimization algorithms, which tend to have a large search-space. We have some exciting research challenges ahead...!