AI can develop prejudice without human input

MIT researchers found that robots in groups can be prejudice to AIs in other groups

Robots fighting

There is a danger that human prejudices will make their way into AI, but research from MIT claims that robots can learn it from themselves.

Researchers set up a simulated game using groups of AI-powered robots, whereby each chooses to donate to another within a group it belonged to or another group it didn't. The robots in the test based decisions on the reputation of each robot and the individual robot's donation strategies.

Advertisement - Article continues below

The researchers used thousands of simulations and the robots learned new strategies by copying each other, either within their own groups or across the entire population. The study found the robots copied strategies that gave them a better payoff in the short term.

As such, the results found that robots became increasingly prejudiced against those from other groups they have not learnt from, and the researchers noted that groups of autonomous machines could demonstrate prejudice by simply identifying, copying and learning behaviour from one another.

"Our simulations show that prejudice is a powerful force of nature and through evolution, it can easily become incentivized in virtual populations, to the detriment of wider connectivity with others," wrote Cardiff University's Professor Roger Whitaker, seen via TechCrunch.

"Protection from prejudicial groups can inadvertently lead to individuals forming further prejudicial groups, resulting in a fractured population. Such widespread prejudice is hard to reverse."

Advertisement
Advertisement - Article continues below
Advertisement - Article continues below

This research suggested to the teams that high cognitive ability isn't therefore necessarily required to develop prejudices.

Until now, artificial intelligence that has shown signs of prejudice has been the result of its human interactions, such as Microsoft's ill-fated chatbot 'Tay tweets' that began to post racist content after learning it from other Twitter users.

However, the research from MIT would suggest a limited form of the technology might have that bias as a default, adding more negative points to a field of technology that is increasingly coming under scrutiny. Recently, the incoming president of the British Science Association warned of a fear-driven public backlash over the misconceptions of AI.

Featured Resources

Preparing for long-term remote working after COVID-19

Learn how to safely and securely enable your remote workforce

Download now

Cloud vs on-premise storage: What’s right for you?

Key considerations driving document storage decisions for businesses

Download now

Staying ahead of the game in the world of data

Create successful marketing campaigns by understanding your customers better

Download now

Transforming productivity

Solutions that facilitate work at full speed

Download now
Advertisement

Recommended

Visit/technology/artificial-intelligence-ai/354766/mit-develops-ai-tech-to-edit-outdated-wikipedia
artificial intelligence (AI)

MIT develops AI tech to edit outdated Wikipedia articles

13 Feb 2020

Most Popular

Visit/business-strategy/careers-training/356422/ibm-job-ad-calls-for-12-year-experience-with-6-year-old
Careers & training

IBM job ad calls for 12-years of experience with six-year-old Kubernetes

13 Jul 2020
Visit/business/business-operations/356395/nvidia-overtakes-intel-as-most-valuable-us-chipmaker
Business operations

Nvidia overtakes Intel as most valuable US chipmaker

9 Jul 2020
Visit/development/containers/356391/the-rise-of-containers
Sponsored

The rise of containers

9 Jul 2020