FB pixel

Google introduces machine learning analysis tool to combat AI bias

Categories Biometric R&D  |  Biometrics News
 

Google has unveiled a bias-detection feature for its TensorFlow machine learning web application, dubbed the What-If Tool, in a blog post.

The What-If Tool allows users to view visualizations of model results on the TensorFlow dashboard, test and visualize the results of manual edits to examples from a dataset, and view partial dependence plots showing how changes to a single feature change the model’s predictions.

The tool addresses the difficulties of editing machine learning models, which usually involves writing custom code for each potential “what-if” scenario.

“Not only is this process inefficient, it makes it hard for non-programmers to participate in the process of shaping and improving ML models. One focus of the Google AI PAIR initiative is making it easier for a broad set of people to examine, evaluate, and debug ML systems,” Google AI Software Engineer James Wexler writes in the post.

The post highlights the What-If Tool’s capacity for detecting misclassifications, uncovering biases in algorithms, and investigating the relative performance of models across different subgroups among its other features.

Microsoft and IBM have each introduced measures for reducing bias in AI after public controversy erupted over the issue after an academic research report on facial recognition. Subsequent attention has included examination in hearings by a U.S. House subcommittee.

Article Topics

 |   |   | 

Latest Biometrics News

 

Cyber Threat Observatory workshop advises on protections for national digital ID systems

The Alan Turing Institute launched the Cyber Threat Observatory last year to monitor cyber threats to digital ID systems. The…

 

Kyrgyzstan state printer wades into biometric passport market with Namibia deal

A shipment of 130,000 biometric passports has been sent from Kyrgyzstan to Namibia, after a contract was signed between the…

 

Spanish law among most comprehensive for age checks, kids’ online safety

Among EU nations pursuing child online safety legislation and age verification tools, Spain has been at the forefront. It has…

 

UN cautions govts to safeguard human rights in AI procurement

AI is a major trend of this decade with advancements in the technology having an effect across society, for both…

 

Optimistic plan would pair universal legal identity with basic income program

A new paper calls the lack of legal identity for millions of people around the world one of the “most…

 

Facia declares breakthrough deepfake detection scores

Facia has reached the point where it is scoring perfect accuracy for deepfake detection on third-party datasets, including Meta’s. The…

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Biometric Market Analysis

Most Viewed This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events