Resources

Resources

Controlling bias in artificial intelligence
Controlling bias in artificial intelligence

Project that strives to come up with fast, novel algorithms that can solve the bias issue.

View
Fair Distributions from Biased Samples- A Maximum Entropy Optimization Framework
Fair Distributions from Biased Samples: A Maximum Entropy Optimization Framework

This article explores ways of fixing biased data to make it better resemble real underlying distributions in the population.

View
Balanced Ranking
Balanced Ranking

Balanced ranking prototype demonstrates that it is possible to be fair while only losing a small amount of value.

View
Image Search
News search

Balanced search is a prototype aimed at demonstrating novel algorithms that can be used for delivering diverse content.

View
News Search
News Search

Balanced search is a prototype aimed at demonstrating novel algorithms that can be used for delivering diverse content.

View
Fair Multiwinner Elections
Fair Multiwinner Elections

Prototype aimed to demonstrate 'fair' voting algorithms.

View
Online Ads
Online Ads

A framework which can serve fair advertisements, + allows the platform to control the fraction of each sensitive-type an advertiser’s ad gets shown to while maximizing its ad revenues.

View