東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Probabilistic Siamese network for le...

Liu, Chen.

Linked to FindBook

Google Book

Amazon

博客來

Probabilistic Siamese network for learning representations.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Probabilistic Siamese network for learning representations./
Author:	Liu, Chen.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2013,
Description:	54 p.
Notes:	Source: Masters Abstracts International, Volume: 76-06.
Contained By:	Masters Abstracts International76-06.
Subject:	Electrical engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1571140
ISBN:	9781321408324

Probabilistic Siamese network for learning representations.
Liu, Chen.

Probabilistic Siamese network for learning representations. - Ann Arbor : ProQuest Dissertations & Theses, 2013 - 54 p.

Source: Masters Abstracts International, Volume: 76-06.

Thesis (M.A.Sc.)--University of Toronto (Canada), 2013.

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

We explore the training of deep neural networks to produce vector representations using weakly labelled information in the form of binary similarity labels for pairs of training images. Previous methods such as siamese networks, IMAX and others, have used fixed cost functions such as L 1, L2-norms and mutual information to drive the representations of similar images together and different images apart. In this work, we formulate learning as maximizing the likelihood of binary similarity labels for pairs of input images, under a parameterized probabilistic similarity model. We describe and evaluate several forms of the similarity model that account for false positives and false negatives differently. We extract representations of MNIST, AT&T ORL and COIL-100 images and use them to obtain classification results. We compare these results with state-of-the-art techniques such as deep neural networks and convolutional neural networks. We also study our method from a dimensionality reduction prospective.

ISBN: 9781321408324Subjects--Topical Terms:

649834
Electrical engineering.

Probabilistic Siamese network for learning representations.
LDR:02105nmm a2200325 4500 001 2209458
005 20191104073441.5
008 201008s2013 ||||||||||||||||| ||eng d
020 $a 9781321408324
035 $a (MiAaPQ)AAI1571140
035 $a (MiAaPQ)utoronto:43097
035 $a AAI1571140
040 $a MiAaPQ $c MiAaPQ
100 1 $a Liu, Chen. $3 641973
245 1 0 $a Probabilistic Siamese network for learning representations.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2013
300 $a 54 p.
500 $a Source: Masters Abstracts International, Volume: 76-06.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Frey, Brendan.
502 $a Thesis (M.A.Sc.)--University of Toronto (Canada), 2013.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a We explore the training of deep neural networks to produce vector representations using weakly labelled information in the form of binary similarity labels for pairs of training images. Previous methods such as siamese networks, IMAX and others, have used fixed cost functions such as L 1, L2-norms and mutual information to drive the representations of similar images together and different images apart. In this work, we formulate learning as maximizing the likelihood of binary similarity labels for pairs of input images, under a parameterized probabilistic similarity model. We describe and evaluate several forms of the similarity model that account for false positives and false negatives differently. We extract representations of MNIST, AT&T ORL and COIL-100 images and use them to obtain classification results. We compare these results with state-of-the-art techniques such as deep neural networks and convolutional neural networks. We also study our method from a dimensionality reduction prospective.
590 $a School code: 0779.
650 4 $a Electrical engineering. $3 649834
690 $a 0544
710 2 $a University of Toronto (Canada). $b Electrical and Computer Engineering. $3 2096349
773 0 $t Masters Abstracts International $g 76-06.
790 $a 0779
791 $a M.A.Sc.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1571140