Build more inclusive TensorFlow pipelines with fairness indicators /

Machine learning (ML) continues to drive monumental change across products and industries. But as we expand the reach of ML to even more sectors and users, it's ever more critical to ensure that these pipelines work well for all users. Tulsee Doshi and Christina Greer outline their insights fro...

Full description

Saved in:
Bibliographic Details
Main Authors: Doshi, Tulsee (Author), Greer, Christina (Author)
Corporate Author: Safari, an O'Reilly Media Company.
Format: eBook
Language:English
Published: O'Reilly Media, Inc., 2020.
Edition:1st edition.
Subjects:
Online Access:CONNECT
CONNECT
LEADER 03545cgm a2200517Ma 4500
001 in00006082555
006 m o d
007 cr cnu||||||||
008 200220s2020 xx --- vleng
005 20220712182517.1
035 |a 1WRLDSHRon1143019008 
040 |a AU@  |b eng  |c AU@  |d UMI  |d UAB  |d OCLCF  |d TOH  |d OCLCO 
019 |a 1176539492  |a 1191047501  |a 1224591225  |a 1232111241  |a 1256358097  |a 1305891702 
020 |z 0636920373377 
024 8 |a 0636920373391 
035 |a (OCoLC)1143019008  |z (OCoLC)1176539492  |z (OCoLC)1191047501  |z (OCoLC)1224591225  |z (OCoLC)1232111241  |z (OCoLC)1256358097  |z (OCoLC)1305891702 
037 |a CL0501000126  |b Safari Books Online 
050 4 |a Q325.5 
049 |a TXMM 
100 1 |a Doshi, Tulsee,  |e author. 
245 1 0 |a Build more inclusive TensorFlow pipelines with fairness indicators /  |c Doshi, Tulsee. 
250 |a 1st edition. 
264 1 |b O'Reilly Media, Inc.,  |c 2020. 
300 |a 1 online resource (1 video file, approximately 36 min.) 
336 |a two-dimensional moving image  |b tdi  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
347 |a video file 
520 |a Machine learning (ML) continues to drive monumental change across products and industries. But as we expand the reach of ML to even more sectors and users, it's ever more critical to ensure that these pipelines work well for all users. Tulsee Doshi and Christina Greer outline their insights from their work in proactively building for fairness, using case studies built from Google products. They also explain the metrics that have been fundamental in evaluating their models at scale and the techniques that have proven valuable in driving improvements. Tulsee and Christina announce the launch of Fairness Indicators and demonstrate how the product can help with more inclusive development. Fairness Indicators is a new feature built into TensorFlow Extended (TFX) and on top of TensorFlow Model Analysis. Fairness Indicators enables developers to compute metrics that identify common fairness risks and drive improvements. You'll leave with an awareness of how algorithmic bias might manifest in your product, the ways you could measure and improve performance, and how Google's Fairness Indicators can help. Prerequisite knowledge A basic understanding of TensorFlow (useful but not required) What you'll learn Learn how to tactically identify and evaluate ML fairness risks using Fairness Indicators. 
542 |f Copyright © O'Reilly Media, Inc. 
550 |a Made available through: Safari, an O'Reilly Media Company. 
511 0 |a Presenter, Tulsee Doshi, Christina Greer. 
590 |a O'Reilly Online Learning Platform: Academic Edition (SAML SSO Access) 
650 0 |a Machine learning. 
650 0 |a Artificial intelligence. 
655 7 |a Electronic videos.  |2 local 
700 1 |a Greer, Christina,  |e author. 
710 2 |a Safari, an O'Reilly Media Company. 
730 0 |a WORLDSHARE SUB RECORDS 
856 4 0 |u https://go.oreilly.com/middle-tennessee-state-university/library/view/-/0636920373391/?ar  |z CONNECT  |3 O'Reilly  |t 0 
949 |a ho0 
994 |a 92  |b TXM 
998 |a wi 
999 f f |s 4cc0ec4e-5726-4f15-bf50-bbf0ad04ee57  |i 9bb301c7-eb89-461a-b263-9f9288936eeb  |t 0 
952 f f |a Middle Tennessee State University  |b Main  |c James E. Walker Library  |d Electronic Resources  |t 1  |e Q325.5   |h Library of Congress classification 
856 4 0 |3 O'Reilly  |t 0  |u https://go.oreilly.com/middle-tennessee-state-university/library/view/-/0636920373391/?ar  |z CONNECT