直近一年間の累計
アクセス数 : ?
ダウンロード数 : ?
ID 118049
著者
Nsinga, Robert Tokushima University
キーワード
embedded system
IEEE 754-2008 floating-point
digital signal processor
Q format notation
資料タイプ
学術雑誌論文
抄録
Using less electric power or speeding up processing is catching the interests of researchers in deep learning. Quantization has offered distillation mechanisms that substitute floating numbers for integers, but little has been suggested about the floating numbers themselves. The use of Q-format notation reduces computational overheads that frees resources for the introduction of more operations. Our experiments, conditioned on varying regimes, introduce automatic differentiation on algorithms like the fast Fourier transforms and Winograd minimal filtering to reduce computational complexity (expressed in total number of MACs) and suggest a path towards the assistive intelligence concept. Empirical results show that, under specific heuristics, the Q-format number notation can overcome the shortfalls of floating numbers, especially for embedded systems. Further benchmarks like the FPBench standard give more details by comparing our proposals with common deep learning operations.
掲載誌名
Journal of Signal Processing
ISSN
18801013
出版者
Research Institute of Signal Processing
26
5
開始ページ
131
終了ページ
140
発行日
2022-09-01
備考
利用は著作権の範囲内に限られる。
EDB ID
出版社版DOI
出版社版URL
フルテキストファイル
言語
eng
著者版フラグ
出版社版
部局
理工学系