國立虎尾科技大學 |

登入

回首頁

Deep learning for computer architects /

Reagen, Brandon,

Deep learning for computer architects /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Deep learning for computer architects // Brandon Reagen ... [et al.].
其他作者:	Reagen, Brandon,
出版者:	[San Rafael, California] :Morgan & Claypool Publishers, : c2017. ,
面頁冊數:	xiv, 109 p. :ill. ; : 24 cm. ;
標題:	Neural networks (Computer science) -
ISBN:	9781627057288 (pbk.) :

Deep learning for computer architects /
Deep learning for computer architects /Brandon Reagen ... [et al.]. - [San Rafael, California] :Morgan & Claypool Publishers,c2017. - xiv, 109 p. :ill. ;24 cm. - Synthesis lectures on computer architecture,#41 1935-3235 ;. - Synthesis lectures in computer architecture ;#41 .

Includes bibliographical references (p. 91-106)

Preface -- Introduction -- Foundations of deep learning --Methods and models -- Neural network accelerator optimization : a case study -- A literature survey and review -- Conclusion

"Machine learning, and specifically deep learning, has been hugely disruptive in many fields of computer science.The success of deep learning techniques in solving notoriously difficult classification and regression problems has resulted in their rapid adoption in solving real-world problems. The emergence of deep learning is widely attributed to a virtuous cycle whereby fundamental advancements in training deeper models were enabled by theavailability of massive datasets and high-performance computer hardware. This text serves as a primer for computer architects in a new and rapidly evolving field. We review how machine learning has evolved since its inception in the 1960s and track the key developments leading up to the emergence of the powerful deep learning techniques that emerged in the last decade. Next we reviewrepresentative workloads, including the most commonly useddatasets and seminal networks across a variety of domains.In addition to discussing the workloads themselves, we also detail the most popular deep learning tools and show how aspiring practitioners can use the tools with the workloads to characterize and optimize DNNs. The remainderof the book is dedicated to the design and optimization ofhardware and architectures for machine learning. As high-performance hardware was so instrumental in the success ofmachine learning becoming a practical solution, this chapter recounts a variety of optimizations proposed recently to further improve future designs. Finally, we present a review of recent research published in the area as well as a taxonomy to help readers understand how various contributions fall in context."--Page 4 of cover

ISBN: 9781627057288 (pbk.) :NT1611Subjects--Topical Terms:

676148
Neural networks (Computer science)

LC Class. No.: Q325.5 / .R434 2017

Dewey Class. No.: 006.31

Deep learning for computer architects /
LDR:02680cam a2200265 a 450 001 882996
003 OCoLC
005 20180111021344.0
008 180314s2017 caua b 000 0 eng c
020 $a 9781627057288 (pbk.) : $c NT1611
020 $a 1627057285 (pbk.)
020 $z 9781627059855 (electronic book)
035 $a (OCoLC)1017739421
035 $a 1017739421
040 $a ZNT $b eng $c NFU $d OBE
041 0 $a eng
042 $a pcc
050 4 $a Q325.5 $b .R434 2017
082 0 4 $a 006.31 $2 23
245 0 0 $a Deep learning for computer architects / $c Brandon Reagen ... [et al.].
260 $a [San Rafael, California] : $b Morgan & Claypool Publishers, $c c2017.
300 $a xiv, 109 p. : $b ill. ; $c 24 cm.
490 1 $a Synthesis lectures on computer architecture, $x 1935-3235 ; $v #41
504 $a Includes bibliographical references (p. 91-106)
505 0 $a Preface -- Introduction -- Foundations of deep learning --Methods and models -- Neural network accelerator optimization : a case study -- A literature survey and review -- Conclusion
520 $a "Machine learning, and specifically deep learning, has been hugely disruptive in many fields of computer science.The success of deep learning techniques in solving notoriously difficult classification and regression problems has resulted in their rapid adoption in solving real-world problems. The emergence of deep learning is widely attributed to a virtuous cycle whereby fundamental advancements in training deeper models were enabled by theavailability of massive datasets and high-performance computer hardware. This text serves as a primer for computer architects in a new and rapidly evolving field. We review how machine learning has evolved since its inception in the 1960s and track the key developments leading up to the emergence of the powerful deep learning techniques that emerged in the last decade. Next we reviewrepresentative workloads, including the most commonly useddatasets and seminal networks across a variety of domains.In addition to discussing the workloads themselves, we also detail the most popular deep learning tools and show how aspiring practitioners can use the tools with the workloads to characterize and optimize DNNs. The remainderof the book is dedicated to the design and optimization ofhardware and architectures for machine learning. As high-performance hardware was so instrumental in the success ofmachine learning becoming a practical solution, this chapter recounts a variety of optimizations proposed recently to further improve future designs. Finally, we present a review of recent research published in the area as well as a taxonomy to help readers understand how various contributions fall in context."--Page 4 of cover
650 0 $a Neural networks (Computer science) $3 676148
650 0 $a Machine learning $3 1137474
650 0 $a Computer architecture $3 1137473
700 1 $a Reagen, Brandon, $e author $3 1137471
830 0 $a Synthesis lectures in computer architecture ; $v #41 $3 1137472