Story image

How mathematics can limit gender bias in AI & ML

26 Nov 2019
Twitter
Facebook

Three major universities have released a new research paper that outlines how machine learning designers can safeguard their creations against the undesirable effects of racial and gender bias.

Researchers from Stanford University, the University of Massachusetts Amherst and the Universidade Federal do Rio Grande do Sol published a paper called Preventing undesirable behavior of intelligent machines.

The paper explains that mathematical criteria could allow a machine learning platform to train artificial intelligence (AI) to avoid unwanted outcomes.

If ‘unsafe’ or ‘unfair’ outcomes can be defined in terms of mathematics, then it could be possible to create algorithms that learn how to avoid these outcomes.

“We want to advance AI that respects the values of its human users and justifies the trust we place in autonomous systems,” explains Stanford assistant professor of computer science and senior author of the paper, Emma Brunskill.

The researchers also wanted to develop a set of techniques that would make it easy for users to specify what sorts of unwanted behaviour they want to constrain and enable machine learning designers to predict with confidence that a system trained using past data can be relied upon when it is applied in real-world circumstances.

THEY TESTED THEIR THEORIES BY TRYING TO IMPROVE THE FAIRNESS of algorithms that predict GPAs of college students based on exam results, which researchers say is a common practice that can result in gender bias. As a result of the testing, the algorithm exhibited less synthetic gender bias than existing methods.

According to researchers, existing methods have no inbuilt fairness filter, or the algorithms designed to achieve fairness are too limited in scope.

“We show how the designers of machine learning algorithms can make it easier for people who want to build AI into their products and services to describe unwanted outcomes or behaviours that the AI system will avoid with high-probability,” says University of Massachusetts Amherst assistant professor of computer science and first author of the paper, Philip Thomas.

The researchers propose that a ‘Seldonian framework’ will make it easier for machine learning designers to build behaviour-avoidance instructions into all sorts of algorithms, in a way that can enable them to assess the probability that trained systems will function properly in the real world.

“Thinking about how we can create algorithms that best respect values like safety and fairness is essential as society increasingly relies on AI,” Brunskill concludes.

The research was supported in part by Adobe, the US National Science Foundation and the US Institute of Educational Sciences.

Story image
Yesterday
Micron publishes annual Diversity, Equality and Inclusion report
“Micron believes that collaboration across our diverse workforce is the key to unlocking strength and innovation, and we are passionate about building a culture of inclusion where all team members are seen, heard, valued and respected.”More
Story image
22 Oct
Allianz executive swap program creates stronger company culture
Allianz is doing its bit to create a strong company culture – by creating a new human resources (HR) programme that allows senior executives to shadow their colleagues.More
Story image
20 Nov
New CFO for ServiceNow, CEO assumes role
"Gina is the right person to join me and our leadership team, help continue ServiceNow's remarkable momentum, and drive our next phase of shared growth and success with our customers."More
Story image
08 Nov
Cohesity appoints Cathy Conroy as Asia Pacific head of alliances
Conroy will be based out of Brisbane as she facilitates rapid organisational growth through the ongoing recruitment and management of an ever-increasing cohort of cloud, storage, and software partners.More
Story image
12 Nov
Citrix appoints new VP of worldwide channel sales & ecosystem
Bronwyn Hastings be responsible for Citrix’s global partner sales, go-to-market partner programs and partner marketing for all Citrix products.More
Story image
16 Oct
APAC lights the way for women in executive roles
Organisations in Asia Pacific and the United States have more women in management than organisations in Europe – and globally, female representation on boards has doubled in the space of just 10 years.More