國立虎尾科技大學 |

Theory and practice of quality assurance for machine learning systems = an experiment-driven approach /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Theory and practice of quality assurance for machine learning systems/ by Samuel Ackerman ... [et al.].
其他題名:	an experiment-driven approach /
其他作者:	Ackerman, Samuel.
出版者:	Cham :Springer Nature Switzerland : : 2024.,
面頁冊數:	xii, 182 p. :ill. (some col.), digital ; : 24 cm.;
Contained By:	Springer Nature eBook
標題:	Machine learning - Quality control. -
電子資源:	https://doi.org/10.1007/978-3-031-70008-8
ISBN:	9783031700088

Theory and practice of quality assurance for machine learning systems = an experiment-driven approach /
Theory and practice of quality assurance for machine learning systemsan experiment-driven approach /[electronic resource] :by Samuel Ackerman ... [et al.]. - Cham :Springer Nature Switzerland :2024. - xii, 182 p. :ill. (some col.), digital ;24 cm.

1. Introduction -- 2. Scientific Analysis of ML Systems -- 3. Motivation and Best Practices for Machine Learning Designers and Testers -- 4. Unit Test vs. System Test of ML Based Systems -- 5. ML Testing -- 6. Principles of Drift Detection and ML Solution Retraining -- 7. Drift Detection by Measuring Distribution Differences -- 8. Sequential Drift Detection -- 9. Drift in Characterizations of Data -- 10. A Framework Analysis for Alternating Components and Drift -- 11. Optimal Integration of the ML Solution in the Business Decision Process -- 12. Testing Solutions Based on Large Language Models -- 13. A Detailed Chatbot Example.

This book is a self-contained introduction to engineering and testing machine learning (ML) systems. It systematically discusses and teaches the art of crafting and developing software systems that include and surround machine learning models. Crafting ML based systems that are business-grade is highly challenging, as it requires statistical control throughout the complete system development life cycle. To this end, the book introduces an "experiment first" approach, stressing the need to define statistical experiments from the beginning of the development life cycle and presenting methods for careful quantification of business requirements and identification of key factors that impact business requirements. Applying these methods reduces the risk of failure of an ML development project and of the resultant, deployed ML system. The presentation is complemented by numerous best practices, case studies and practical as well as theoretical exercises and their solutions, designed to facilitate understanding of the ideas, concepts and methods introduced. The goal of this book is to empower scientists, engineers, and software developers with the knowledge and skills necessary to create robust and reliable ML software.

ISBN: 9783031700088

Standard No.: 10.1007/978-3-031-70008-8doiSubjects--Topical Terms:

1462437
Machine learning
--Quality control.

LC Class. No.: Q325.5

Dewey Class. No.: 006.31

Theory and practice of quality assurance for machine learning systems = an experiment-driven approach /
LDR:02918nam a2200325 a 4500 001 1138629
003 DE-He213
005 20241026125744.0
006 m d
007 cr nn 008maaau
008 250117s2024 sz s 0 eng d
020 $a 9783031700088 $q (electronic bk.)
020 $a 9783031700071 $q (paper)
024 7 $a 10.1007/978-3-031-70008-8 $2 doi
035 $a 978-3-031-70008-8
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5
072 7 $a UMZ $2 bicssc
072 7 $a COM051230 $2 bisacsh
072 7 $a UMZ $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.5 $b .T396 2024
245 0 0 $a Theory and practice of quality assurance for machine learning systems $h [electronic resource] : $b an experiment-driven approach / $c by Samuel Ackerman ... [et al.].
260 $a Cham : $c 2024. $b Springer Nature Switzerland : $b Imprint: Springer,
300 $a xii, 182 p. : $b ill. (some col.), digital ; $c 24 cm.
505 0 $a 1. Introduction -- 2. Scientific Analysis of ML Systems -- 3. Motivation and Best Practices for Machine Learning Designers and Testers -- 4. Unit Test vs. System Test of ML Based Systems -- 5. ML Testing -- 6. Principles of Drift Detection and ML Solution Retraining -- 7. Drift Detection by Measuring Distribution Differences -- 8. Sequential Drift Detection -- 9. Drift in Characterizations of Data -- 10. A Framework Analysis for Alternating Components and Drift -- 11. Optimal Integration of the ML Solution in the Business Decision Process -- 12. Testing Solutions Based on Large Language Models -- 13. A Detailed Chatbot Example.
520 $a This book is a self-contained introduction to engineering and testing machine learning (ML) systems. It systematically discusses and teaches the art of crafting and developing software systems that include and surround machine learning models. Crafting ML based systems that are business-grade is highly challenging, as it requires statistical control throughout the complete system development life cycle. To this end, the book introduces an "experiment first" approach, stressing the need to define statistical experiments from the beginning of the development life cycle and presenting methods for careful quantification of business requirements and identification of key factors that impact business requirements. Applying these methods reduces the risk of failure of an ML development project and of the resultant, deployed ML system. The presentation is complemented by numerous best practices, case studies and practical as well as theoretical exercises and their solutions, designed to facilitate understanding of the ideas, concepts and methods introduced. The goal of this book is to empower scientists, engineers, and software developers with the knowledge and skills necessary to create robust and reliable ML software.
650 0 $a Machine learning $x Quality control. $3 1462437
650 1 4 $a Software Engineering. $3 669632
650 2 4 $a Artificial Intelligence. $3 646849
700 1 $a Ackerman, Samuel. $3 1462436
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-3-031-70008-8
950 $a Professional and Applied Computing (SpringerNature-12059)