Explainable AI for practitioners : (Record no. 98116)

MARC details
000 -LEADER
fixed length control field 02047cam a22002297i 4500
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 230703t20222023cc a b 001 0 eng d
015 ## - NATIONAL BIBLIOGRAPHY NUMBER
National bibliography number GBC2J5983
Source bnb
016 7# - NATIONAL BIBLIOGRAPHIC AGENCY CONTROL NUMBER
Record control number 020791265
Source Uk
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
International Standard Book Number 9789355422439
042 ## - AUTHENTICATION CODE
Authentication code lccopycat
082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 005.74015
Cutter MUN
100 1# - MAIN ENTRY--PERSONAL NAME
Personal name Munn, Michael
245 10 - TITLE STATEMENT
Title Explainable AI for practitioners :
Remainder of title designing and implementing explainable ML solutions
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT)
Place of publication, distribution, etc Mumbai
Name of publisher, distributor, etc Shroff Publishers & Distributors Pvt. Ltd.
Date of publication, distribution, etc 2023
300 ## - PHYSICAL DESCRIPTION
Extent xvi, 259 pages :
520 ## - Remark
Summary, etc Most intermediate-level machine learning books focus on how to optimize models by increasing accuracy or decreasing prediction error. But this approach often overlooks the importance of understanding why and how your ML model makes the predictions that it does.<br/><br/>Explainability methods provide an essential toolkit for better understanding model behavior, and this practical guide brings together best-in-class techniques for model explainability. Experienced machine learning engineers and data scientists will learn hands-on how these techniques work so that you'll be able to apply these tools more easily in your daily workflow.<br/><br/>This essential book provides:<br/><br/>A detailed look at some of the most useful and commonly used explainability techniques, highlighting pros and cons to help you choose the best tool for your needs<br/>Tips and best practices for implementing these techniques<br/>A guide to interacting with explainability and how to avoid common pitfalls<br/>The knowledge you need to incorporate explainability in your ML workflow to help build more robust ML systems<br/>Advice about explainable AI techniques, including how to apply techniques to models that consume tabular, image, or text data<br/>Example implementation code in Python using well-known explainability libraries for models built in Keras and TensorFlow 2.0, PyTorch, and HuggingFace
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element Machine learning.
650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element Machine learning.
Source of heading or term fast
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name Pitman, David
Titles and other words associated with a name (Engineer),
906 ## - LOCAL DATA ELEMENT F, LDF (RLIN)
a Business Analytics
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Item type Book
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Home library Current library Shelving location Date acquired Source of acquisition Cost, normal purchase price Programme Full call number Barcode Date last seen Cost, replacement price Koha item type
    Dewey Decimal Classification     Main Library Main Library Analytics 29/11/2023 6038 880.00   005.74015 MUN 119068 29/11/2023 1100.00 Book

Powered by Koha