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

Preventing Overfitting in Deep Learn...

Khatri, Alizishaan Anwar Hussein.

FindBook

Google Book

Amazon

博客來

Preventing Overfitting in Deep Learning Using Differential Privacy.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Preventing Overfitting in Deep Learning Using Differential Privacy./
作者:	Khatri, Alizishaan Anwar Hussein.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
面頁冊數:	51 p.
附註:	Source: Masters Abstracts International, Volume: 79-07.
Contained By:	Masters Abstracts International79-07.
標題:	Computer Engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10622959
ISBN:	9780355311082

Preventing Overfitting in Deep Learning Using Differential Privacy.
Khatri, Alizishaan Anwar Hussein.

Preventing Overfitting in Deep Learning Using Differential Privacy. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 51 p.

Source: Masters Abstracts International, Volume: 79-07.

Thesis (M.S.)--State University of New York at Buffalo, 2017.

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

The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and text datasets. They have been shown to be powerful systems that are capable of learning detailed relationships and abstractions from the data. This is a double-edged sword which makes such systems vulnerable to learning the noise in the training set, thereby negatively impacting performance. This is also known as the problem of overfitting or poor generalization. In a practical setting, analysts typically have limited data to build models that must generalize to unseen data. In this work, we explore the use of a differential-privacy based approach to improve generalization in Deep Neural Networks.

ISBN: 9780355311082Subjects--Topical Terms:

1567821
Computer Engineering.

Preventing Overfitting in Deep Learning Using Differential Privacy.
LDR:01823nmm a2200337 4500 001 2207508
005 20190920131242.5
008 201008s2017 ||||||||||||||||| ||eng d
020 $a 9780355311082
035 $a (MiAaPQ)AAI10622959
035 $a (MiAaPQ)buffalo:15489
035 $a AAI10622959
040 $a MiAaPQ $c MiAaPQ
100 1 $a Khatri, Alizishaan Anwar Hussein. $3 3434497
245 1 0 $a Preventing Overfitting in Deep Learning Using Differential Privacy.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 51 p.
500 $a Source: Masters Abstracts International, Volume: 79-07.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Gaboardi, Marco.
502 $a Thesis (M.S.)--State University of New York at Buffalo, 2017.
506 $a This item must not be sold to any third party vendors.
520 $a The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and text datasets. They have been shown to be powerful systems that are capable of learning detailed relationships and abstractions from the data. This is a double-edged sword which makes such systems vulnerable to learning the noise in the training set, thereby negatively impacting performance. This is also known as the problem of overfitting or poor generalization. In a practical setting, analysts typically have limited data to build models that must generalize to unseen data. In this work, we explore the use of a differential-privacy based approach to improve generalization in Deep Neural Networks.
590 $a School code: 0656.
650 4 $a Computer Engineering. $3 1567821
650 4 $a Information science. $3 554358
650 4 $a Computer science. $3 523869
690 $a 0464
690 $a 0723
690 $a 0984
710 2 $a State University of New York at Buffalo. $b Computer Science and Engineering. $3 1035503
773 0 $t Masters Abstracts International $g 79-07.
790 $a 0656
791 $a M.S.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10622959