itb-nz logo
Story image

How mathematics can limit gender bias in AI & ML

26 Nov 2019

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.

Link image
<span class="coloured">Unleash the intelligent way to automate at Pega Discover – Intelligent Automation</span>
Find out how the world’s largest brands are accelerating business and simplifying systems in this two-hour, interactive virtual event. By the end you’ll be primed to start getting business done smarter and faster while scaling toward your biggest business goals. Register Now.More
Story image
Video: 10 Minute IT Jams - Who is Globalization Partners?
Today, Techday speaks to Globalization Partners general manager for Asia-Pacific Charles Ferguson, who talks about Employer of Record technology and its strategic advantage for companies looking to expand internationally.More
Download image
Network functions virtualisation: What is is, how to use it, and why it matters
Network functions virtualisation (NFV) is fast becoming the go-to method of simplifying corporate networks from planning, through deployment and management.More
Story image
SecOps opens new Cyber Defence Operations Centre in Auckland
Privacy Commissioner John Edwards officially opened the centre this week, recognising SecOps’ efforts to provide managed security services to New Zealand businesses.More
Story image
Schneider brings AI to fight against energy consumption
The investment into adding AI-assisted advising to its energy and sustainability services aims to promote efficiency and a total reduction of clients’ emissions.More
Story image
APAC network-attached storage revenue to reach $8.9 billion
Network attached storage has emerged as a viable alternative to the traditional storage mechanism in the Asia Pacific.More