摘要：

       Deep learning, also known as deep structured learning or hierarchical learning, is part of a broader family of machine learning methods based on learning data representations. In recent years, deep learning has been mainly applied to a few fields, including computer vision, speech recognition, natural language processing and audio processing etc. In this talk, I will focus on some non-traditional applications that deep learning can also be applied and found it generates good results. These applications include sensor data analytics for remaining useful life (RUL) prediction and human activity recognition, traffic crowd density prediction and traffic anomaly detection.

主讲人介绍：

     Xiaoli is currently data analytics department head at the Institute for Infocomm Research, A*STAR, Singapore. He also holds adjunct positions at School of Computer Science and Engineering, Nanyang Technological University. His research interests include data mining, machine learning, artificial intelligence, and bioinformatics. He has published more than 170 peer-reviewed papers, including top tier conferences, such as KDD, ICDM, SDM, PKDD/ECML, PAKDD, ICDE, ICML, IJCAI, AAAI, ACL, SIGIR, EMNLP, CIKM, UbiCom etc, as well as some top tier journals such as IEEE Transactions TKDE, IEEE Transactions on Reliability, Bioinformatics. He has been serving as the (Senior) PC members/workshop chairs/session chairs in the leading data mining/machine learning related conferences, including KDD, ICDM, SDM, PKDD/ECML, WWW, IJCAI, AAAI, ACL, and CIKM. Some of his representative research publications include: positive unlabelled based learning (more than 2000 citations), social/biological network mining (more than 1000 citations). He also received 4 Best Paper Awards from reputable international conferences and 2 Best Performance Awards from international benchmark competitions.

        该讲座是前沿讲座，欢迎全校师生踊跃参加。

计算机学院

校学术委员会

智能通信软件与多媒体北京市重点实验室