國立虎尾科技大學 |

Language: English

Back

Practicing trustworthy machine learning : = consistent, transparent, and fair AI pipelines /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Practicing trustworthy machine learning :/ Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar.
Reminder of title:	consistent, transparent, and fair AI pipelines /
remainder title:	Consistent, transparent, and fair artifical intelligence pipelines
Author:	Pruksachatkun, Yada,
other author:	McAteer, Matthew,
Published:	Sebastopol, CA :O'Reilly Media, Inc., : 2023.,
Description:	xxiv, 274 p. :ill. ; : 23 cm.;
Subject:	Machine learning. -
ISBN:	9781098120276 (pbk.) :

Practicing trustworthy machine learning : = consistent, transparent, and fair AI pipelines /
Pruksachatkun, Yada,

Practicing trustworthy machine learning :consistent, transparent, and fair AI pipelines /Consistent, transparent, and fair artifical intelligence pipelinesYada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar. - 1st ed. - Sebastopol, CA :O'Reilly Media, Inc.,2023. - xxiv, 274 p. :ill. ;23 cm.

Includes bibliographic references and index.

Preface --

"With the increasing use of AI in high-stakes domains such as medicine, law, and defense, organizations spend a lot of time and money to make ML models trustworthy. Many books on the subject offer deep dives into theories and concepts. This guide provides a practical starting point to help development teams produce models that are secure, more robust, less biased, and more explainable. Authors Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar translate best practices in the academic literature for curating datasets and building models into a blueprint for building industry-grade trusted ML systems. With this book, engineers and data scientists will gain a much-needed foundation for releasing trustworthy ML applications into a noisy, messy, and often hostile world" --

ISBN: 9781098120276 (pbk.) :NT2656

LCCN: 2023278332

Nat. Bib. No.: GBC307044bnb

Nat. Bib. Agency Control No.: 020868348UkSubjects--Topical Terms:

561253
Machine learning.

LC Class. No.: Q325.5 / .P78 2023

Dewey Class. No.: 006.3/1

Practicing trustworthy machine learning : = consistent, transparent, and fair AI pipelines /
LDR:02222cam a2200301 a 4500 001 1137278
003 OCoLC
005 20241210051143.0
008 241219s2023 caua b 001 0 eng d
010 $a 2023278332
015 $a GBC307044 $2 bnb
016 7 $a 020868348 $2 Uk
019 $a 1313386935
020 $a 9781098120276 (pbk.) : $c NT2656
020 $a 1098120272 (pbk.)
035 $a (OCoLC)1313074094 $z (OCoLC)1313386935
035 $a on1313074094
040 $a YDX $b eng $c NFU $d BDX $d UKMGB $d OCLCQ $d GO9 $d OCLCF $d DLC $d CQC $d OCL $d OCLCO $d CDX $d IG#
041 0 # $a eng
050 0 0 $a Q325.5 $b .P78 2023
082 0 4 $a 006.3/1 $2 23
100 1 $a Pruksachatkun, Yada, $e author. $3 1460360
245 1 0 $a Practicing trustworthy machine learning : $b consistent, transparent, and fair AI pipelines / $c Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar.
246 3 # $a Consistent, transparent, and fair artifical intelligence pipelines
250 $a 1st ed.
260 # $a Sebastopol, CA : $b O'Reilly Media, Inc., $c 2023.
300 $a xxiv, 274 p. : $b ill. ; $c 23 cm.
504 $a Includes bibliographic references and index.
505 0 0 $t Preface -- $t Privacy -- $t Fairness and bias -- $t Model explainability and interpretability -- $t Robustness -- $t Secure and trustworthy data generation -- $t More state-of-the-art research questions -- $t From theory to practice -- $t An ecosystem of trust -- $t Synthetic data generation tools -- $t Other interpretability and explainability tool kits -- $t Index -- $t About the authors.
520 # $a "With the increasing use of AI in high-stakes domains such as medicine, law, and defense, organizations spend a lot of time and money to make ML models trustworthy. Many books on the subject offer deep dives into theories and concepts. This guide provides a practical starting point to help development teams produce models that are secure, more robust, less biased, and more explainable. Authors Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar translate best practices in the academic literature for curating datasets and building models into a blueprint for building industry-grade trusted ML systems. With this book, engineers and data scientists will gain a much-needed foundation for releasing trustworthy ML applications into a noisy, messy, and often hostile world" -- $c Provided by publisher.
650 # 0 $a Machine learning. $3 561253
650 # 0 $a Artificial intelligence $x Philosophy. $3 574201
650 # 0 $a Algorithms. $3 527865
650 # 0 $a Data mining. $3 528622
700 1 # $a McAteer, Matthew, $e author. $3 1460361
700 1 # $a Majumdar, Subhabrata, $e author. $3 1460362