IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Special Section on Parallel, Distributed, and Reconfigurable Computing, and Networking
Relationship between Recognition Accuracy and Numerical Precision in Convolutional Neural Network Models
Yasuhiro NAKAHARAMasato KIYAMAMotoki AMAGASAKIMasahiro IIDA
著者情報
ジャーナル フリー

2020 年 E103.D 巻 12 号 p. 2528-2529

詳細
抄録

Quantization is an important technique for implementing convolutional neural networks on edge devices. Quantization often requires relearning, but relearning sometimes cannot be always be applied because of issues such as cost or privacy. In such cases, it is important to know the numerical precision required to maintain accuracy. We accurately simulate calculations on hardware and accurately measure the relationship between accuracy and numerical precision.

著者関連情報
© 2020 The Institute of Electronics, Information and Communication Engineers
前の記事 次の記事
feedback
Top