User 'Martin' contributed resource 'Machine learning classifiers are up to 20% less accurate when labeling photos from homes in poor countries'

June 17, 2019 11:56:00 AM CEST: User Martin contributed resource Machine learning classifiers are up to 20% less accurate when labeling photos from homes in poor countries with the following metadata:

associatedDate:
creator: Cory Doctorow
description: A new study from Facebook AI Research evaluates common machine-learning classifiers' ability to label photos of objects found in households in rich countries versus household objects from poor countries and finds that the models' performance lags significantly when being asked to classify the possessions of poor people. Partly that's due to differences in the objects…
language:
license:
publisher:
resourceType: resource-bookmark
rightsHolder:
tags: ml
title: Machine learning classifiers are up to 20% less accurate when labeling photos from homes in poor countries

[ALOE] Recent activities on resource "Machine learning classifiers are up to 20% less accurate when labeling photos from homes in poor countries"

User 'Martin' contributed resource 'Machine learning classifiers are up to 20% less accurate when labeling photos from homes in poor countries'