東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Distributed Deep Learning in Iot : = Splitting Neural Networks in Inference and Training.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Distributed Deep Learning in Iot :/
其他題名:	Splitting Neural Networks in Inference and Training.
作者:	Guo, Jia.
面頁冊數:	1 online resource (82 pages)
附註:	Source: Masters Abstracts International, Volume: 84-02.
Contained By:	Masters Abstracts International84-02.
標題:	Wireless networks. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29229406click for full text (PQDT)
ISBN:	9798841563259

Distributed Deep Learning in Iot : = Splitting Neural Networks in Inference and Training.
Guo, Jia.

Distributed Deep Learning in Iot :Splitting Neural Networks in Inference and Training. - 1 online resource (82 pages)

Source: Masters Abstracts International, Volume: 84-02.

Thesis (M.A.Sc.)--Queen's University (Canada), 2022.

Includes bibliographical references

In this thesis, we first propose a scheme to solve the inference problem of Network of Neural Networks (NoNN) under changing channel conditions. The proposed scheme is composed of two methods: two devices work in parallel and one device works with the server. Error Correction Codes (ECC) are also applied to deal with the errors during data transmitting. Our scheme is to find the optimal method and code rate of ECC to maximize the accuracy within a specific delay threshold. Experiment results show that the proposed scheme performs much better than the other schemes for inference of NoNN under changing channel environment compared with other schemes with a single method or fixed code rate.We then propose a scheme applying Online Knowledge Distillation via Collaboratively Learning (KDCL) to Split Learning to get a distilled model of server-part model in SplitNN after training. The distilled model could be designed to fit the memory-limited Internet of Things (IoT) devices so that clients could get prediction results independently after receiving the distilled model from the server. In this way, high communication latency and costs between client and server can be avoided. Experiments show that the proposed scheme could successfully get a distilled model after training. Besides, the accuracies of both the original model and distilled model could get a significant improvement compared with baseline models.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798841563259Subjects--Topical Terms:

1531264
Wireless networks.
Index Terms--Genre/Form:

542853
Electronic books.

Distributed Deep Learning in Iot : = Splitting Neural Networks in Inference and Training.
LDR:02752nmm a2200397K 4500 001 2362546
005 20231102121822.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798841563259
035 $a (MiAaPQ)AAI29229406
035 $a (MiAaPQ)QueensUCan_197430060
035 $a AAI29229406
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Guo, Jia. $3 3433762
245 1 0 $a Distributed Deep Learning in Iot : $b Splitting Neural Networks in Inference and Training.
264 0 $c 2022
300 $a 1 online resource (82 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: Masters Abstracts International, Volume: 84-02.
500 $a Advisor: Kim, Il-Min.
502 $a Thesis (M.A.Sc.)--Queen's University (Canada), 2022.
504 $a Includes bibliographical references
520 $a In this thesis, we first propose a scheme to solve the inference problem of Network of Neural Networks (NoNN) under changing channel conditions. The proposed scheme is composed of two methods: two devices work in parallel and one device works with the server. Error Correction Codes (ECC) are also applied to deal with the errors during data transmitting. Our scheme is to find the optimal method and code rate of ECC to maximize the accuracy within a specific delay threshold. Experiment results show that the proposed scheme performs much better than the other schemes for inference of NoNN under changing channel environment compared with other schemes with a single method or fixed code rate.We then propose a scheme applying Online Knowledge Distillation via Collaboratively Learning (KDCL) to Split Learning to get a distilled model of server-part model in SplitNN after training. The distilled model could be designed to fit the memory-limited Internet of Things (IoT) devices so that clients could get prediction results independently after receiving the distilled model from the server. In this way, high communication latency and costs between client and server can be avoided. Experiments show that the proposed scheme could successfully get a distilled model after training. Besides, the accuracies of both the original model and distilled model could get a significant improvement compared with baseline models.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Wireless networks. $3 1531264
650 4 $a Deep learning. $3 3554982
650 4 $a Collaboration. $3 3556296
650 4 $a Error correction & detection. $3 3480646
650 4 $a Communication. $3 524709
650 4 $a Neural networks. $3 677449
650 4 $a Computer engineering. $3 621879
650 4 $a Internet of Things. $3 3538511
650 4 $a Servers. $3 3220915
650 4 $a Computer science. $3 523869
650 4 $a Electrical engineering. $3 649834
650 4 $a Engineering. $3 586835
650 4 $a Web studies. $3 2122754
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0464
690 $a 0459
690 $a 0800
690 $a 0984
690 $a 0544
690 $a 0537
690 $a 0646
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Queen's University (Canada). $3 1017786
773 0 $t Masters Abstracts International $g 84-02.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29229406 $z click for full text (PQDT)