JournalArta
Sunday, November 22, 2026 · JakartaS&P 6,910.39 ▼3.70%USD/IDR 18,158 ▼0.42%
JournalArta
Global Edition
beyond headlines
Advertisement

Artificial Intelligence Models Differ From Brains, York Study Finds

York University researchers found that AI models can predict brain-cell responses to images without processing visual information in the same way as the brain. The team has released a testing toolkit to help scientists identify which parts of their models correspond to neural activity.

By matthew jonathan
WIB2 min read
Artificial Intelligence Models Differ From Brains, York Study Finds
Artificial Intelligence Models Differ From Brains, York Study Finds

York University researchers have found that artificial intelligence models can predict brain-cell responses to images without necessarily processing them like the brain. The study tested artificial neural networks, computer systems that can perform tasks such as recognizing objects in pictures.

The distinction matters for scientists who use those models to investigate how people see. A model that produces a brain-like response may still rely on different internal processes, the researchers found.

“Artificial intelligence systems are often described as 'brain-like' because they can predict activity in parts of the brain that help us recognize objects,” said York University Assistant Professor Kohitij Kar, the study’s senior author.

Advertisement

Researchers Tested Predictions in Reverse

The York University team tested whether recorded brain activity could predict features inside AI models. Scientists had generally tested the relationship in the other direction: whether models could predict brain activity, Kar said.

The researchers developed a method called reverse predictivity testing. It examines whether similarities between models and brain activity hold when the prediction runs both ways.

AI models generally predicted the responses of recorded neurons, the specialized cells that transmit information in the brain. The neurons’ responses were much less effective at predicting many internal features of those models.

Advertisement

Kar said the same problem did not appear when researchers compared neural activity across different brains. The result suggests that a model can match brain responses while using different internal mechanisms.

“The findings suggest that today's AI systems solve visual tasks partly using internal strategies that the brain may not use,” Kar said. He added that the parts of AI models aligned with the brain were better at predicting human behavior.

Images Tested Across Visual Styles

The team examined responses to 1,320 natural photographs and realistic synthetic images. Those pictures showed 10 subjects: a bear, an elephant, a face, an apple, a car, a dog, a chair, a plane, a bird and a zebra.

Advertisement

The subjects appeared against natural scenes and indoor or outdoor backgrounds. Another 300 images showed the same subjects as outlines, drawings, simplified representations and artistic interpretations.

York Postdoctoral Fellow Sabine Muzellec, who worked on the study, said models previously considered brain-like relied on internal components the brain did not appear to use.

Team Releases Testing Toolkit

The York University researchers released a public toolkit for developers to test their AI models. The approach helps identify which model features correspond to brain activity, Kar said.

Kar said the method was especially important for the team’s autism research program. That work uses models of the neurotypical brain, meaning one with neurological development and functioning generally considered typical, as a baseline.

The study was published in Nature Machine Intelligence.

Advertisement
What Kind of Holiday Spender Are You? Take the Black Friday QuizTake the quizWhat Kind of Holiday Spender Are You? Take the Black Friday QuizStart →
Advertisement
Most Read
  1. 1Magnitude 4.2 Earthquake Wakes Los Angeles Before DawnMagnitude 4.2 Earthquake Wakes Los Angeles Before Dawn
  2. 2Micron Says Memory Has Changed as Shares Fall 13.89%Micron Says Memory Has Changed as Shares Fall 13.89%
  3. 3Dow Jones Futures Await Reopening After Tech Stocks SlideDow Jones Futures Await Reopening After Tech Stocks Slide
  4. 4GTA 6 Draws Review Bombing on MetacriticGTA 6 Draws Review Bombing on Metacritic
  5. 5ORCL Stock Week Ahead: Levels and Scenarios for November 23–27ORCL Stock Week Ahead: Levels and Scenarios for November 23–27
Advertisement
Don't Miss

Latest News

All stories →
  1. Motorola Moto Tag 3 Appears on Amazon With Familiar SpecsTechnology · GadgetsMotorola Moto Tag 3 Appears on Amazon With Familiar SpecsNov 22
  2. Menopause Wellness Booths Sell Women Tequila and MushroomsLifestyle · Food & HealthMenopause Wellness Booths Sell Women Tequila and MushroomsNov 22
  3. Trump Orders Contractors to Coordinate Congressional RepliesWorld · United StatesTrump Orders Contractors to Coordinate Congressional RepliesNov 22
  4. Vampire Camel Found in Museum Fossil CollectionTechnologyVampire Camel Found in Museum Fossil CollectionNov 22
  5. Advertisement
  6. Theresa May Urges Andy Burnham to Drop EU Reentry TalkWorld · EuropeTheresa May Urges Andy Burnham to Drop EU Reentry TalkNov 22
  7. Retiring in Thailand Costs One Couple $3,000 to $3,500 a MonthAsia · Southeast AsiaRetiring in Thailand Costs One Couple $3,000 to $3,500 a MonthNov 22
  8. GTA VI Gets 5.6 User Score on Metacritic, Compared With 99 From CriticsTechnology · GamingGTA VI Gets 5.6 User Score on Metacritic, Compared With 99 From CriticsNov 22
  9. India Set to Add 200 Million Home Air ConditionersBusiness · EnergyIndia Set to Add 200 Million Home Air ConditionersNov 22