Draft Title: Applied Edge AI: Towards Efficient Deep Model Design and Multi-Edge Inference
Draft Abstract: This talk will introduce Applied Edge AI regarding market needs, challenges, and technology trends. Later, the speaker will present the recent progress of a very efficient deep model - Binary Neural Network (BNN), including the development process and the latest model design. Especially, he will show some results of BNNs in accuracy and energy consumption using hardware simulation. The speaker will further introduce an open source software for Edge AI: KubeEdge/Sedna, and he will demonstrate a compelling use case: multi-edge person ReID for smart-campus.
Speaker Bio: Haojin Yang received the Doctoral Degree with the final grade “summa cum laude” at Hasso-Plattner-Institute (HPI) and the University of Potsdam in 2013. From 2015 to 2019, He was the multimedia and machine learning (MML) research group leader at HPI. He received German full professor's teaching qualification (Habilitation) in July 2019. From 2019 to 2020, he was the Edge Computing Lab branch head at AI Labs and Ali-Cloud of Alibaba Group. Currently, he leads the MML research group at HPI and serves as chief scientific advisor of Huawei edge cloud innovation lab. He has authored and co-authored more than 70 high quality papers in peer reviewed international conferences and journals. He served as PC/SPC member for leading conferences such as NeurIPS, ICML, ICLR, CVPR, ICCV, AAAI etc.