English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Algorithmic decision making based on computer vision and machine learningtechnologies continue to permeate our lives. But issues related to biases ofthese models and the extent to which they treat certain segments of thepopulation unfairly, have led to concern in the general public. It is nowaccepted that because of biases in the datasets we present to the models, afairness-oblivious training will lead to unfair models. An interesting topic isthe study of mechanisms via which the de novo design or training of the modelcan be informed by fairness measures. Here, we study mechanisms that imposefairness concurrently while training the model. While existing fairness basedapproaches in vision have largely relied on training adversarial modulestogether with the primary classification/regression task, in an effort toremove the influence of the protected attribute or variable, we show how ideasbased on well-known optimization concepts can provide a simpler alternative. Inour proposed scheme, imposing fairness just requires specifying the protectedattribute and utilizing our optimization routine. We provide a detailedtechnical analysis and present experiments demonstrating that various fairnessmeasures from the literature can be reliably imposed on a number of trainingtasks in vision in a manner that is interpretable.

FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret