國立虎尾科技大學 |

登入

回首頁

Deep networks : = Applications, inte...

University of Massachusetts Boston.

Deep networks : = Applications, interpretability, and optimization.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Deep networks :/
其他題名:	Applications, interpretability, and optimization.
作者:	Lo, Henry Z.
面頁冊數:	1 online resource (61 pages)
附註:	Source: Dissertation Abstracts International, Volume: 77-11(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781339798431

Deep networks : = Applications, interpretability, and optimization.
Lo, Henry Z.

Deep networks :Applications, interpretability, and optimization. - 1 online resource (61 pages)

Source: Dissertation Abstracts International, Volume: 77-11(E), Section: B.

Thesis (Ph.D.)--University of Massachusetts Boston, 2016.

Includes bibliographical references

Deep neural networks are the current state-of-the-art in computer vision. In the first section, we apply these networks to the problem of crater detection, demonstrating that being able to learn filters end-to-end with a classifier is superior than existing techniques. Our models achieve state-of-the-art performance on a standard crater detection task. In the second section, we propose a measure of unit importance in neural networks. We demonstrate that using this measure, the unique features and locations of an image can be extracted and analyzed. Results also demonstrate some interesting properties of unit importance in neural nets, and we show several use cases of our measure on a face recognition data set. Finally, we address optimization difficulties unique to neural nets, and propose a new method of weight initialization which leads to better performance for deeper networks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781339798431Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Deep networks : = Applications, interpretability, and optimization.
LDR:02023ntm a2200313K 4500 001 913634
005 20180622095234.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781339798431
035 $a (MiAaPQ)AAI10118513
035 $a (MiAaPQ)umb:10735
035 $a AAI10118513
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Lo, Henry Z. $3 1186548
245 1 0 $a Deep networks : $b Applications, interpretability, and optimization.
264 0 $c 2016
300 $a 1 online resource (61 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: Dissertation Abstracts International, Volume: 77-11(E), Section: B.
500 $a Adviser: Wei Ding.
502 $a Thesis (Ph.D.)--University of Massachusetts Boston, 2016.
504 $a Includes bibliographical references
520 $a Deep neural networks are the current state-of-the-art in computer vision. In the first section, we apply these networks to the problem of crater detection, demonstrating that being able to learn filters end-to-end with a classifier is superior than existing techniques. Our models achieve state-of-the-art performance on a standard crater detection task. In the second section, we propose a measure of unit importance in neural networks. We demonstrate that using this measure, the unique features and locations of an image can be extracted and analyzed. Results also demonstrate some interesting properties of unit importance in neural nets, and we show several use cases of our measure on a face recognition data set. Finally, we address optimization difficulties unique to neural nets, and propose a new method of weight initialization which leads to better performance for deeper networks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Massachusetts Boston. $b Computer Science. $3 1179593
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10118513 $z click for full text (PQDT)

筆 0 讀者評論

多媒體

評論

新增評論分享你的心得

Export

取書館別