建國科技大學圖書館 |

語系: 繁體中文

說明(常見問題)

圖書館個人資料蒐集告知聲明

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Efficient processing of deep neural ...

Sze, Vivienne.

Efficient processing of deep neural networks

紀錄類型:	書目-語言資料,印刷品 : 單行本
其他作者:	SzeVivienne.,
出版地:	[San Rafael, California]
出版者:	Morgan & Claypool Publishers;
出版年:	c2020.
面頁冊數:	xxi, 319 p.ill. (some col.) : 24 cm.;
集叢名:	Synthesis lectures on computer architecturelecture #50
標題:	Big data -
標題:	Data mining -
標題:	Invisible Web -
標題:	Machine learning - Industrial applications -
標題:	Neural networks (Computer science) -
摘要註:	"This book provides a structured treatment of the key principles and techniques for enabling efficient processing of deep neural networks (DNNs). DNNs are currently widely used for many artificial intelligence (AI) applications, including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at the cost of high computational complexity. Therefore, techniques that enable efficient processing of deep neural networks to improve metrics-such as energy-efficiency, throughput, and latency-without sacrificing accuracy or increasing hardware costs are critical to enabling the wide deployment of DNNs in AI systems. The book includes background on DNN processing; a description and taxonomy of hardware architectural approaches for designing DNN accelerators; key metrics for evaluating and comparing different designs; features of the DNN processing that are amenable to hardware/algorithm co-design to improve energy efficiency and throughput; and opportunities for applying new technologies. Readers will find a structured introduction to the field as well as a formalization and organization of key concepts from contemporary works that provides insights that may spark new ideas"--Back cover.
ISBN:	9781681738352

Efficient processing of deep neural networks
Efficient processing of deep neural networks / Vivienne Sze ... [et al.] - [San Rafael, California] : Morgan & Claypool Publishers, c2020.. - xxi, 319 p. ; ill. (some col.) ; 24 cm.. - (Synthesis lectures on computer architecture ; lecture #50).
Includes bibliographical references (p. 283-316).
ISBN 9781681738352ISBN 168173835XISBN 9781681738314ISBN 1681738317
Big dataData miningInvisible WebMachine learningNeural networks (Computer science) -- Industrial applications

Sze, Vivienne.

Efficient processing of deep neural networks
LDR:02213cam a2200265 450 001 393738
010 1 $a 9781681738352 $b hbk. $d NT3060
010 1 $a 168173835X $b hbk.
010 1 $a 9781681738314 $b pbk.
010 1 $a 1681738317 $b pbk.
010 1 $z 9781681738321 $b ebk.
100 $a 20210910d2020 k y0engy50 b
101 0 $a eng
102 $a us
105 $a a a 000yy
200 1 $a Efficient processing of deep neural networks $f Vivienne Sze ... [et al.]
210 $a [San Rafael, California] $c Morgan & Claypool Publishers $d c2020.
215 1 $a xxi, 319 p. $c ill. (some col.) $d 24 cm.
225 2 $a Synthesis lectures on computer architecture $v lecture #50 $x 1935-3235
320 $a Includes bibliographical references (p. 283-316)
330 $a "This book provides a structured treatment of the key principles and techniques for enabling efficient processing of deep neural networks (DNNs). DNNs are currently widely used for many artificial intelligence (AI) applications, including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at the cost of high computational complexity. Therefore, techniques that enable efficient processing of deep neural networks to improve metrics-such as energy-efficiency, throughput, and latency-without sacrificing accuracy or increasing hardware costs are critical to enabling the wide deployment of DNNs in AI systems. The book includes background on DNN processing; a description and taxonomy of hardware architectural approaches for designing DNN accelerators; key metrics for evaluating and comparing different designs; features of the DNN processing that are amenable to hardware/algorithm co-design to improve energy efficiency and throughput; and opportunities for applying new technologies. Readers will find a structured introduction to the field as well as a formalization and organization of key concepts from contemporary works that provides insights that may spark new ideas"--Back cover.
410 0 $1 2001 $a Synthesis lectures on computer architecture $v 50.
410 0 $1 2001 $a Synthesis lectures on computer architecture $v lecture #50 $x 1935-3235
606 $a Big data $2 lc $3 305097
606 $a Data mining $2 lc $3 66445
606 $a Invisible Web $2 lc $3 386012
606 $a Machine learning $x Industrial applications $2 lc $3 386013
606 $a Neural networks (Computer science) $2 lc $3 39781
676 $a 006.32
680 $a QA76.87 $b .S944 2020
702 1 $a Sze $b Vivienne. $3 386011
801 0 $a cw $b CTU $c 20210910 $g AACR2