Article Type
Changed
Thu, 12/15/2022 - 15:40

 

Artificial intelligence (AI)–powered neural networks modeled on real human brain connectivity patterns perform cognitive tasks better than traditional AI systems, new research suggests. “This work opens new opportunities to discover how the network organization of the brain optimizes cognitive capacity,” wrote researchers from The Neuro (Montreal Neurological Institute–Hospital) and the Quebec Artificial Intelligence Institute.

Courtesy Dr. Bratislav Misic
Dr. Bratislav Misic

Senior investigator Bratislav Misic, PhD, said the research has potential clinical application for studying diseases of the brain, which is something his team is actively working on. “For example, using MRI techniques, we can measure different patterns of atrophy in neurodegenerative diseases such as Alzheimer’s disease,” he said.

“We can use these disease patterns from real patients to artificially lesion these connectomes and to ask how a particular disease causes a particular pattern of symptoms and cognitive deficits,” he added.

The findings were published online in Nature Machine Intelligence.

Unique approach

Using brain imaging data, the investigators reconstructed a human brain connectivity pattern and applied it to an artificial neural network. After training, the artificial neural network successfully performed a working memory task more flexibly and efficiently than other “benchmark” AI systems.

The researchers noted that their approach is unique because previous work on brain connectivity, also known as connectomics, has focused on describing brain organization without regard to how it actually functions.

Traditional artificial neural network have arbitrary structures that do not reflect how real brain networks are organized. Integrating brain connectomics into the construction of artificial neural network can reveal how the wiring of the brain supports specific cognitive skills, the investigators wrote.

“Up until now, if you look at how neural networks are constructed, the architectures that are used are very ad hoc and very problem specific,” Dr. Misic said. “But the connectomics revolution that’s happened in neuroscience over the past 20 years or so has given us the ability to really measure and trace out connection patterns in a variety of organisms, including the human brain.”

He noted that the researchers took wiring patterns of the real human brain and implemented it as an artificial neural network. They then “trained that network to perform a very simple cognitive task, and when you compare it to other benchmark architectures, it actually does better.”

This shows that there is “something fundamentally different about how the human brain is wired up and that the design principles that we can see in the human brain could be used to potentially build better artificial networks,” Dr. Misic concluded.

Funding for the research was provided by the Canada First Research Excellence Fund, awarded to McGill University for the Healthy Brains, Healthy Lives initiative, and by the Natural Sciences and Engineering Research Council of Canada, Fonds de Recherche du Quebec – Santé, the Canadian Institute for Advanced Research, Canada Research Chairs, Fonds de Recherche du Quebec – Nature et Technologies, and the Centre UNIQUE (Union of Neuroscience and Artificial Intelligence). The investigators have reported no relevant financial relationships.

A version of this article first appeared on Medscape.com.

Issue
Neurology Reviews- 29(10)
Publications
Topics
Sections

 

Artificial intelligence (AI)–powered neural networks modeled on real human brain connectivity patterns perform cognitive tasks better than traditional AI systems, new research suggests. “This work opens new opportunities to discover how the network organization of the brain optimizes cognitive capacity,” wrote researchers from The Neuro (Montreal Neurological Institute–Hospital) and the Quebec Artificial Intelligence Institute.

Courtesy Dr. Bratislav Misic
Dr. Bratislav Misic

Senior investigator Bratislav Misic, PhD, said the research has potential clinical application for studying diseases of the brain, which is something his team is actively working on. “For example, using MRI techniques, we can measure different patterns of atrophy in neurodegenerative diseases such as Alzheimer’s disease,” he said.

“We can use these disease patterns from real patients to artificially lesion these connectomes and to ask how a particular disease causes a particular pattern of symptoms and cognitive deficits,” he added.

The findings were published online in Nature Machine Intelligence.

Unique approach

Using brain imaging data, the investigators reconstructed a human brain connectivity pattern and applied it to an artificial neural network. After training, the artificial neural network successfully performed a working memory task more flexibly and efficiently than other “benchmark” AI systems.

The researchers noted that their approach is unique because previous work on brain connectivity, also known as connectomics, has focused on describing brain organization without regard to how it actually functions.

Traditional artificial neural network have arbitrary structures that do not reflect how real brain networks are organized. Integrating brain connectomics into the construction of artificial neural network can reveal how the wiring of the brain supports specific cognitive skills, the investigators wrote.

“Up until now, if you look at how neural networks are constructed, the architectures that are used are very ad hoc and very problem specific,” Dr. Misic said. “But the connectomics revolution that’s happened in neuroscience over the past 20 years or so has given us the ability to really measure and trace out connection patterns in a variety of organisms, including the human brain.”

He noted that the researchers took wiring patterns of the real human brain and implemented it as an artificial neural network. They then “trained that network to perform a very simple cognitive task, and when you compare it to other benchmark architectures, it actually does better.”

This shows that there is “something fundamentally different about how the human brain is wired up and that the design principles that we can see in the human brain could be used to potentially build better artificial networks,” Dr. Misic concluded.

Funding for the research was provided by the Canada First Research Excellence Fund, awarded to McGill University for the Healthy Brains, Healthy Lives initiative, and by the Natural Sciences and Engineering Research Council of Canada, Fonds de Recherche du Quebec – Santé, the Canadian Institute for Advanced Research, Canada Research Chairs, Fonds de Recherche du Quebec – Nature et Technologies, and the Centre UNIQUE (Union of Neuroscience and Artificial Intelligence). The investigators have reported no relevant financial relationships.

A version of this article first appeared on Medscape.com.

 

Artificial intelligence (AI)–powered neural networks modeled on real human brain connectivity patterns perform cognitive tasks better than traditional AI systems, new research suggests. “This work opens new opportunities to discover how the network organization of the brain optimizes cognitive capacity,” wrote researchers from The Neuro (Montreal Neurological Institute–Hospital) and the Quebec Artificial Intelligence Institute.

Courtesy Dr. Bratislav Misic
Dr. Bratislav Misic

Senior investigator Bratislav Misic, PhD, said the research has potential clinical application for studying diseases of the brain, which is something his team is actively working on. “For example, using MRI techniques, we can measure different patterns of atrophy in neurodegenerative diseases such as Alzheimer’s disease,” he said.

“We can use these disease patterns from real patients to artificially lesion these connectomes and to ask how a particular disease causes a particular pattern of symptoms and cognitive deficits,” he added.

The findings were published online in Nature Machine Intelligence.

Unique approach

Using brain imaging data, the investigators reconstructed a human brain connectivity pattern and applied it to an artificial neural network. After training, the artificial neural network successfully performed a working memory task more flexibly and efficiently than other “benchmark” AI systems.

The researchers noted that their approach is unique because previous work on brain connectivity, also known as connectomics, has focused on describing brain organization without regard to how it actually functions.

Traditional artificial neural network have arbitrary structures that do not reflect how real brain networks are organized. Integrating brain connectomics into the construction of artificial neural network can reveal how the wiring of the brain supports specific cognitive skills, the investigators wrote.

“Up until now, if you look at how neural networks are constructed, the architectures that are used are very ad hoc and very problem specific,” Dr. Misic said. “But the connectomics revolution that’s happened in neuroscience over the past 20 years or so has given us the ability to really measure and trace out connection patterns in a variety of organisms, including the human brain.”

He noted that the researchers took wiring patterns of the real human brain and implemented it as an artificial neural network. They then “trained that network to perform a very simple cognitive task, and when you compare it to other benchmark architectures, it actually does better.”

This shows that there is “something fundamentally different about how the human brain is wired up and that the design principles that we can see in the human brain could be used to potentially build better artificial networks,” Dr. Misic concluded.

Funding for the research was provided by the Canada First Research Excellence Fund, awarded to McGill University for the Healthy Brains, Healthy Lives initiative, and by the Natural Sciences and Engineering Research Council of Canada, Fonds de Recherche du Quebec – Santé, the Canadian Institute for Advanced Research, Canada Research Chairs, Fonds de Recherche du Quebec – Nature et Technologies, and the Centre UNIQUE (Union of Neuroscience and Artificial Intelligence). The investigators have reported no relevant financial relationships.

A version of this article first appeared on Medscape.com.

Issue
Neurology Reviews- 29(10)
Issue
Neurology Reviews- 29(10)
Publications
Publications
Topics
Article Type
Sections
Article Source

FROM NATURE MACHINE INTELLIGENCE

Citation Override
Publish date: August 27, 2021
Disallow All Ads
Content Gating
No Gating (article Unlocked/Free)
Alternative CME
Disqus Comments
Default
Use ProPublica
Hide sidebar & use full width
render the right sidebar.
Conference Recap Checkbox
Not Conference Recap
Clinical Edge
Display the Slideshow in this Article
Medscape Article
Display survey writer
Reuters content
Disable Inline Native ads
WebMD Article