Nonlinear Theory and Its Applications, IEICE
Online ISSN : 2185-4106
ISSN-L : 2185-4106
Special Issue on Recent Progress in Nonlinear Theory and Its Applications
A study on a low power optimization algorithm for an edge-AI device
Tatsuya KanekoKentaro OrimoItaru HidaShinya Takamaeda-YamazakiMasayuki IkebeMasato MotomuraTetsuya Asai
Author information
JOURNAL FREE ACCESS

2019 Volume 10 Issue 4 Pages 373-389

Details
Abstract

Although research on the inference phase of edge artificial intelligence (AI) has made considerable improvement, the required training phase remains an unsolved problem. Neural network (NN) processing has two phases: inference and training. In the training phase, a NN incurs high calculation cost. The number of bits (bitwidth) in the training phase is several orders of magnitude larger than that in the inference phase. Training algorithms, optimized to software, are not appropriate for training hardware-oriented NNs. Therefore, we propose a new training algorithm for edge AI: backpropagation (BP) using a ternarized gradient. This ternarized backpropagation (TBP) provides a balance between calculation cost and performance. Empirical results demonstrate that in a two-class classification task, TBP works well in practice and compares favorably with 16-bit BP (Fixed-BP).

Content from these authors
© 2019 The Institute of Electronics, Information and Communication Engineers
Previous article Next article
feedback
Top