大葉大學圖書館 |

Federated learning[electronic resource] /

紀錄類型:	書目-電子資源 : Monograph/item
杜威分類號:	006.31
書名/作者:	Federated learning/ Qiang Yang, Yang Liu, Yong Cheng, Yan Kang, Tianjian Chen, Han Yu.
作者:	Yang, Qiang,
其他作者:	Liu, Yang,
面頁冊數:	1 online resource (209 p.)
標題:	Machine learning.
標題:	Federated database systems.
標題:	Data protection.
ISBN:	1681736985
ISBN:	9781681736976
ISBN:	9781681736983
ISBN:	9781681736990
書目註:	Includes bibliographical references (pages 155-186).
摘要、提要註:	How is it possible to allow multiple data owners to collaboratively train and use a shared prediction model while keeping all the local training data private? Traditional machine learning approaches need to combine all data at one location, typically a data center, which may very well violate the laws on user privacy and data confidentiality. Today, many parts of the world demand that technology companies treat user data carefully according to user-privacy laws. The European Union's General Data Protection Regulation (GDPR) is a prime example. In this book, we describe how federated machine learning addresses this problem with novel solutions combining distributed machine learning, cryptography and security, and incentive mechanism design based on economic principles and game theory. We explain different types of privacy-preserving machine learning solutions and their technological backgrounds, and highlight some representative practical use cases. We show how federated learning can become the foundation of next-generation machine learning that caters to technological and societal needs for responsible AI development and application.
電子資源:	https://portal.igpublish.com/iglibrary/search/MCPB0006511.html

Federated learning[electronic resource] /
Yang, Qiang,

Federated learning[electronic resource] /Qiang Yang, Yang Liu, Yong Cheng, Yan Kang, Tianjian Chen, Han Yu. - 1 online resource (209 p.) - Synthesis lectures on artificial intelligence and machine learning. - Synthesis lectures on artificial intelligence and machine learning..

Includes bibliographical references (pages 155-186).

How is it possible to allow multiple data owners to collaboratively train and use a shared prediction model while keeping all the local training data private? Traditional machine learning approaches need to combine all data at one location, typically a data center, which may very well violate the laws on user privacy and data confidentiality. Today, many parts of the world demand that technology companies treat user data carefully according to user-privacy laws. The European Union's General Data Protection Regulation (GDPR) is a prime example. In this book, we describe how federated machine learning addresses this problem with novel solutions combining distributed machine learning, cryptography and security, and incentive mechanism design based on economic principles and game theory. We explain different types of privacy-preserving machine learning solutions and their technological backgrounds, and highlight some representative practical use cases. We show how federated learning can become the foundation of next-generation machine learning that caters to technological and societal needs for responsible AI development and application.

Mode of access: World Wide Web.

ISBN: 1681736985Subjects--Topical Terms:

202931
Machine learning.
Index Terms--Genre/Form:

336502
Electronic books.

LC Class. No.: Q325.5

Dewey Class. No.: 006.31

Federated learning[electronic resource] /
LDR:02206nmm a2200289 i 4500 001 525095
006 m eo d
007 cr cn |||m|||a
008 230513s2019 cau ob 000 0 eng d
020 $a 1681736985
020 $a 9781681736976
020 $a 9781681736983
020 $a 9781681736990
035 $a MCPB0006511
040 $a iG Publishing $b eng $c iG Publishing $e rda
050 0 0 $a Q325.5
082 0 0 $a 006.31
100 1 $a Yang, Qiang, $e author. $3 752795
245 1 0 $a Federated learning $h [electronic resource] / $c Qiang Yang, Yang Liu, Yong Cheng, Yan Kang, Tianjian Chen, Han Yu.
264 1 $a [San Rafael, California] : $b Morgan & Claypool Publishers, $c 2019.
300 $a 1 online resource (209 p.)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
490 1 $a Synthesis lectures on artificial intelligence and machine learning
504 $a Includes bibliographical references (pages 155-186).
520 3 $a How is it possible to allow multiple data owners to collaboratively train and use a shared prediction model while keeping all the local training data private? Traditional machine learning approaches need to combine all data at one location, typically a data center, which may very well violate the laws on user privacy and data confidentiality. Today, many parts of the world demand that technology companies treat user data carefully according to user-privacy laws. The European Union's General Data Protection Regulation (GDPR) is a prime example. In this book, we describe how federated machine learning addresses this problem with novel solutions combining distributed machine learning, cryptography and security, and incentive mechanism design based on economic principles and game theory. We explain different types of privacy-preserving machine learning solutions and their technological backgrounds, and highlight some representative practical use cases. We show how federated learning can become the foundation of next-generation machine learning that caters to technological and societal needs for responsible AI development and application.
538 $a Mode of access: World Wide Web.
650 0 $a Machine learning. $3 202931
650 0 $a Federated database systems. $3 752802
650 0 $a Data protection. $3 339996
655 4 $a Electronic books. $2 local $3 336502
700 1 $a Liu, Yang, $e author. $3 752796
700 1 $a Cheng, Yong, $e author. $3 752797
700 1 $a Kang, Yan, $e author. $3 752798
700 1 $a Chen, Tianjian, $e author. $3 752799
700 1 $a Yu, Han, $e author. $3 752800
830 0 $a Synthesis lectures on artificial intelligence and machine learning. $3 752801
856 4 0 $u https://portal.igpublish.com/iglibrary/search/MCPB0006511.html