itb-au 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.

Story image
New head of Australia and New Zealand operations for SAS
Clunies-Ross brings a broad perspective of the Asia Pacific market, most recently in COO roles with Oracle and Citrix.More
Story image
AR and VR presents huge potential for construction industry, but businesses slow to adopt
According to GlobalData, the construction industry is slowly shifting from years of the wait-and-watch stance to adopting digital technologies to improve the overall project lifecycle from conceptual design to construction.More
Link image
You’re invited: The secrets to workplace happiness in the post-pandemic world
It has been a rough year for workplace wellbeing, with disruption and health concerns worrying every employee. Join Poly’s A/NZ Kickstart 2021 on 10 December from 11am AEDT, where special guest Dr Justin Coulson will share secrets to workplace happiness in the post-pandemic world. Register now.More
Story image
Samsung extends partnership with Google, joins Android Enterprise Recommended programme
Samsung’s participation in the programme gives customers added assurance that its participating products meet the hardware and software requirements set out by Google for the enterprise.More
Story image
Video: 10 Minute IT Jams - Who is OutSystems?
In this IT Jam, we speak with OutSystems vice president for A/NZ Paul Arthur, who discusses the company's role in the A/NZ region, how things have changed for the company and the industry amid pandemic, and what he sees in the future of visual development and digital transformation.More
Story image
Most Australian businesses’ comms not post-pandemic ready
New Zoom research finds that 55% of Australian businesses lack effective tools to communicate effectively in a hybrid workplace world.More