國立虎尾科技大學 |

Efficient Algorithms, Hardware Architectures and Circuits for Deep Learning Accelerators.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Efficient Algorithms, Hardware Architectures and Circuits for Deep Learning Accelerators./
作者:	Wang, Miaorong.
面頁冊數:	1 online resource (138 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-09, Section: B.
Contained By:	Dissertations Abstracts International85-09B.
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798381957211

Efficient Algorithms, Hardware Architectures and Circuits for Deep Learning Accelerators.
Wang, Miaorong.

Efficient Algorithms, Hardware Architectures and Circuits for Deep Learning Accelerators. - 1 online resource (138 pages)

Source: Dissertations Abstracts International, Volume: 85-09, Section: B.

Thesis (Ph.D.)--Massachusetts Institute of Technology, 2023.

Includes bibliographical references

Deep learning has permeated many industries due to its state-of-the-art ability to process complex data and uncover intricate patterns. However, it is computationally expensive. Researchers have shown in theory and practice that the progress of deep learning in many applications is heavily reliant on increases in computing power, and thus leads to increasing energy demand. That may impede further advancement in the field. To tackle that challenge, this thesis presents several techniques to improve the energy efficiency of deep learning accelerators while adhering to the accuracy and throughput requirements of the desired application.First, we develop hybrid dataflows and co-design the memory hierarchy. That enables designers to trade off the reuse between different data types across different storage elements provided by the technology for higher energy efficiency. Second, we propose a weight tuning algorithm and accelerator co-design, which optimizes the bit representation of weights for energy reduction. Last, we present VideoTime, an algorithm and accelerator co-design for efficient real-time video understanding with temporal redundancy reduction and temporal modeling. Our proposed techniques enrich accelerator designers' toolkits, pushing the boundaries of energy efficiency for sustainable advances in deep learning.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381957211Subjects--Topical Terms:

596380
Electrical engineering.
Subjects--Index Terms:

Hardware architecturesIndex Terms--Genre/Form:

554714
Electronic books.

Efficient Algorithms, Hardware Architectures and Circuits for Deep Learning Accelerators.
LDR:02709ntm a22003737 4500 001 1146473
005 20240812064624.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381957211
035 $a (MiAaPQ)AAI31091289
035 $a (MiAaPQ)MIT1721_1_152734
035 $a AAI31091289
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Wang, Miaorong. $3 1471862
245 1 0 $a Efficient Algorithms, Hardware Architectures and Circuits for Deep Learning Accelerators.
264 0 $c 2023
300 $a 1 online resource (138 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-09, Section: B.
500 $a Advisor: Chandrakasan, Anantha P.
502 $a Thesis (Ph.D.)--Massachusetts Institute of Technology, 2023.
504 $a Includes bibliographical references
520 $a Deep learning has permeated many industries due to its state-of-the-art ability to process complex data and uncover intricate patterns. However, it is computationally expensive. Researchers have shown in theory and practice that the progress of deep learning in many applications is heavily reliant on increases in computing power, and thus leads to increasing energy demand. That may impede further advancement in the field. To tackle that challenge, this thesis presents several techniques to improve the energy efficiency of deep learning accelerators while adhering to the accuracy and throughput requirements of the desired application.First, we develop hybrid dataflows and co-design the memory hierarchy. That enables designers to trade off the reuse between different data types across different storage elements provided by the technology for higher energy efficiency. Second, we propose a weight tuning algorithm and accelerator co-design, which optimizes the bit representation of weights for energy reduction. Last, we present VideoTime, an algorithm and accelerator co-design for efficient real-time video understanding with temporal redundancy reduction and temporal modeling. Our proposed techniques enrich accelerator designers' toolkits, pushing the boundaries of energy efficiency for sustainable advances in deep learning.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer engineering. $3 569006
653 $a Hardware architectures
653 $a Deep learning
653 $a Memory hierarchy
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0464
710 2 $a Massachusetts Institute of Technology. $b Department of Electrical Engineering and Computer Science. $3 1467552
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-09B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31091289 $z click for full text (PQDT)