Hiroki Matsutani

Keio University, Japan

On-device Learning of Neural Networks for Wireless Sensor Nodes

Abstract

In this talk, we will introduce a neural-network based on-device learning for field-trainable anomaly detection and its related technologies. In real environments, normal patterns may vary with time due to noises or some other environmental factors. In this case, there is a gap between training data and deployed environments. Our approach addresses this issue by training normal patterns in a placed environment extemporarily. We will introduce some prototype systems and applications of the on-device learning.

Biography

Hiroki Matsutani received the BA, ME, and PhD degrees from Keio University, Yokohama, Japan, in 2004, 2006, and 2008, respectively. He is currently a 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.