Keio University, Japan
An On-Device Learning Approach and Its Extension for Federated Learning
Most edge AI focuses on prediction tasks on resource-limited edge devices, while the training is done at server machines, so retraining a model on the edge devices to reflect environmental changes is a complicated task. To follow such environmental changes, a neural-network based on-device learning approach is recently proposed, so that edge devices can train incoming data at runtime to update their model. However, since a training is done at distributed edge devices, the issue is that only a limited amount of training data can be used for each edge device. To address this issue, this talk presents an on-device federated learning for cooperative model update, where edge devices exchange their intermediate trained results and update their model by using those collected from the other edge devices.
Hiroki Matsutani received the BA, ME, and PhD degrees from Keio University, Yokohama, Japan, in 2004, 2006, and 2008, respectively. He is currently an Associate Professor in the Department of Information and Computer Science, Keio University. His research interests are related to computer architecture, interconnection networks, hardware accelerators, and machine learning algorithms.
If you wish to modify any information or update your photo, please contact the Publicity Chair at the following address: