学术报告
我的位置在: 首页 > 学术报告 > 正文
Machine Learning: From Shallow To Deep
浏览次数:日期:2019-06-06编辑:信科院 科研办

 

时间:2019年6月10日上午10:30

地点:信息科学与工程学院106教室

报告人:何海波教授

简历:

何海波博士是美国罗德岛大学(University of Rhode Island)的讲席教授(Robert Haas Endowed Chair Professor),智能计算与自适应系统实验室主任,IEEE Fellow。

何海波主要从事智能计算以及其在智能电网,大数据,深度学习,机器人应用等方向的研究。已出版学术著作1本,编著1本,编著会议论文集6本,在权威学术期刊和会议上发表论文300多篇。其发表的论文在专业领域产生了深远的影响,包括IEEE Transactions on Knowledgeand Data Engineering上高引用论文(单篇论文引用超过3800次),多篇进入EssentialScience Indicators(ESI) 高引用论文,IEEE Trans. Information Forensics and Security封面论文,IEEE通信协会最佳阅读论文(IEEE Communications Society Best Readings) 等等。其指导的博士生中已有5名在美国和加拿大主要的国家级大学担任助理教授(tenure-track assistant professor),4名获得了中国国家留学基金委评选的“国家优秀自费留学生奖,” 获得海内外大量媒体包括中央电视台的报道,2名获得罗德岛大学最优博士论文奖。何海波目前担任《IEEE神经网络与学习系统汇刊》(IEEE Transactions on Neural Networks and Learning Systems)(影响因子:7.982)的主编 (Editor-in-Chief)。曾担任10多个IEEE各类技术委员会主席和副主席,包括IEEE智能计算协会新兴技术委员会主席(Chair,IEEE CIS Emergent Technology Technical Committee),IEEE智能计算协会神经网络技术委员会主席(Chair, IEEE CIS Neural Network Technical Committee), IEEE智能计算智能电网副主席(Vice Chair ,IEEE CIS Smart Grid Task Force)等等。在世界各地高校、研究机构和学术会议做了80多个邀请报告,包括若干国际学术会议的大会报告(Plenary Speaker)。曾担任20多个国际会议的各类主席职务(General Chair, Program Chair, Finance Chair等等)。

报告摘要:

The recently advancements in artificial/computational intelligence has witnessed tremendous excitements worldwide from academia, industry, and government. This impressive progress not only demonstrated the power of machine learning over complicated tasks, but also provided the opportunity for computational intelligence to play a critical role in a wide range of applications. This talk aims to review and discuss the recent research developments in machine learning, with a focus on the key characteristics from shallow to deep learning. The unique features of the current artificial intelligence wave, together with their driving technology directions, will be discussed. I will also use reinforcement learning (RL), the core science behind the DeepMind’s innovation engine, as an example to show how a deep reinforcement learning system can be developed for improved learning and decision-making process. I will present numerous applications to show-case of the broader and far-reaching applications across different domains such as smart grid, wireless communication systems, and human- robot interaction. As one of the hottest research topics worldwide, I will conclude my talk with several fundamental questions to the community to stimulate serious discussions and thinking in this area.