Summary
International Conference on Emerging Technologies for Communications
2020
Session Number:N1
Session:
Number:N1-3
Distributed Processing Method for Deep Learning on Wireless Sensor Networks
Karin UMEDA, Takashi NISHITSUJI, Takuya ASAKA, Takumi MIYOSHI,
pp.-
Publication Date:2020/12/2
Online ISSN:2188-5079
PDF download
Summary:
In wireless sensor networks, distributed processing technology for deep learning that utilizes edge computing and mobile terminals has been attracting interest.However, although the existing methods improve the data processing speed, there is a problem in which the amount of communication and the load on the server increase. To solve this problem, in this paper, we propose a distributed method that divides the intermediate layers of deep learning into individual sensors.