Abstract:  In this talk I will present our latest research about knowledge transfer graph for Deep Collaborative Learning (DCL), which is a method that incorporates Knowledge Distillation and Deep Mutual Learning. DCL is represented by a directional graph where each model is represented by a node, and the propagation of knowledge from the source node to the target node is represented by edges. In DCL, a hyperparameter search can be used to search for an optimal knowledge transfer graph.

Bio: Dr. Fujiyoshi received his Ph.D. in Electrical Engineering from Chubu University, Japan, in 1997. From 1997 to 2000 he was a post-doctoral fellow at the Robotics Institute of Carnegie Mellon University, Pittsburgh, PA, USA, working on the DARPA Video Surveillance and Monitoring (VSAM) effort and the humanoid vision project for the HONDA Humanoid Robot. He is now a professor of the Department of Robotics, Chubu University, Japan. From 2005 to 2006, he was a visiting researcher at Robotics Institute, Carnegie Mellon University.

Homepage: http://mprg.jp/en/