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

Deep Learning and Subspace Segmentat...

Abdul-Malek, Ayad.

FindBook

Google Book

Amazon

博客來

Deep Learning and Subspace Segmentation: Theory and Applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Learning and Subspace Segmentation: Theory and Applications./
作者:	Abdul-Malek, Ayad.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	85 p.
附註:	Source: Dissertations Abstracts International, Volume: 80-12, Section: B.
Contained By:	Dissertations Abstracts International80-12B.
標題:	Computer Engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13807398
ISBN:	9781392244562

Deep Learning and Subspace Segmentation: Theory and Applications.
Abdul-Malek, Ayad.

Deep Learning and Subspace Segmentation: Theory and Applications. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 85 p.

Source: Dissertations Abstracts International, Volume: 80-12, Section: B.

Thesis (Ph.D.)--Tennessee State University, 2019.

This item must not be sold to any third party vendors.

The first goal of this research is to improve the mathematical understanding of deep convolutional networks by exploring its relation to subspace segmentation. This research develops a set of algorithms that improve the subspace separation. The training stage generated set of automatic features are more separable compared to that of the traditional deep convolutional networks. The new algorithms are to be applied to the object classification problem.The second goal is to develop a novel technique for the segmentation of data W = [w1 · · · wN] ⊂ RD drawn from a union U = ∪Mi = 1 Si of subspaces {Si}Mi = 1. First, an existing subspace segmentation algorithm is used to perform an initial data clustering {Ci}Mi = 1, where Ci = {wi1 ···wik} ⊂ W is the set of data from the ith cluster. Then, a local subspace LSi is matched for each Ci and the distance dij between LSi and each point wij 2 Ci is computed. A data-driven threshold η is computed and the data points (in Ci) whose distances to LSi are larger than η are eliminated since they are considered as outliers or erroneously clustered data points in Ci. The remaining datapoints Ci ⊂ Ci are considered to be coming from the same subspace with high confidence. Then, {Ci}Mi = 1 are used in unsupervised way to train a convolution neural network to obtain a deep learning model, which is in turn used to re-cluster W. The system has been successfully implemented using the MNIST dataset and it improved the segmentation accuracy of a particular algorithm (EnSC-ORGEN) from 93.79% to 96.52%.

ISBN: 9781392244562Subjects--Topical Terms:

1567821
Computer Engineering.

Deep Learning and Subspace Segmentation: Theory and Applications.
LDR:02643nmm a2200337 4500 001 2209046
005 20191025102640.5
008 201008s2019 ||||||||||||||||| ||eng d
020 $a 9781392244562
035 $a (MiAaPQ)AAI13807398
035 $a (MiAaPQ)tnstate:11268
035 $a AAI13807398
040 $a MiAaPQ $c MiAaPQ
100 1 $a Abdul-Malek, Ayad. $3 3436125
245 1 0 $a Deep Learning and Subspace Segmentation: Theory and Applications.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 85 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-12, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Sekmen, Ali.
502 $a Thesis (Ph.D.)--Tennessee State University, 2019.
506 $a This item must not be sold to any third party vendors.
520 $a The first goal of this research is to improve the mathematical understanding of deep convolutional networks by exploring its relation to subspace segmentation. This research develops a set of algorithms that improve the subspace separation. The training stage generated set of automatic features are more separable compared to that of the traditional deep convolutional networks. The new algorithms are to be applied to the object classification problem.The second goal is to develop a novel technique for the segmentation of data W = [w1 · · · wN] ⊂ RD drawn from a union U = ∪Mi = 1 Si of subspaces {Si}Mi = 1. First, an existing subspace segmentation algorithm is used to perform an initial data clustering {Ci}Mi = 1, where Ci = {wi1 ···wik} ⊂ W is the set of data from the ith cluster. Then, a local subspace LSi is matched for each Ci and the distance dij between LSi and each point wij 2 Ci is computed. A data-driven threshold η is computed and the data points (in Ci) whose distances to LSi are larger than η are eliminated since they are considered as outliers or erroneously clustered data points in Ci. The remaining datapoints Ci ⊂ Ci are considered to be coming from the same subspace with high confidence. Then, {Ci}Mi = 1 are used in unsupervised way to train a convolution neural network to obtain a deep learning model, which is in turn used to re-cluster W. The system has been successfully implemented using the MNIST dataset and it improved the segmentation accuracy of a particular algorithm (EnSC-ORGEN) from 93.79% to 96.52%.
590 $a School code: 0840.
650 4 $a Computer Engineering. $3 1567821
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
690 $a 0464
690 $a 0800
690 $a 0984
710 2 $a Tennessee State University. $b Electrical & Computer Engineering. $3 1036279
773 0 $t Dissertations Abstracts International $g 80-12B.
790 $a 0840
791 $a Ph.D.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13807398