Ai Models of the Brain Could serves the ‘Digital Twins’ in Research

Much as a pilot might practical managers in a flight simulator, scientists might soon be able to perform experiments on a realistic simulation of the mouse brain. In a New Study, Stanford Medicine Researchers and Collaborators Used An Artificial Intelligence Model to Build a “Digital Twin” of the part of the mouse brain that processes visual information.

The Digital Twin Was Trained on Large DataSets of Brain Activity ColleCted It coald then predict the response of tens of thousands of neurons to new videos and images.

Digital Twins Could Make Studying the Inner Workings of the Brain Easier and More Efficient.

“If you build the model of the brain and it’s very accurate, that means you can do a lot more experiments,” Said Andreas Tolias, Ph.D., Stanford Medicine Professor of Ophthalmology and Senior Author of the Study Published April 9 in Nature. “The Ones That Are the Most Promising You Can Thes Test In The Real Brain.”

The Lead Author of the Study is Eric Wang, Ph.D., A Medical Student at Baylor College of Medicine.

Beyond the Training Distribution

UNLIKE PREVIOUS AI MODELS OF THE VISUAL CORTEX, WHICH COULD SIMULLA THE BRAIN’S ANSWER TO ONLY THE TYPE OF STIMULI THES SAW IN THE TRAINING DATE, THE NEW MODEL CAN PREDICT THE BRAIN’S RESPONSE TO WIDE RANGE OF NEW VISUAL INPUT. It can even suirise anatomical features of each neuron.

The New Model is an Example of a Foundation Model, Relativery New Class of Models Capable of Learning from Large Datasets, then Applying That Knowledge to New Tasks and New Types of Data –or What Researchers Call “Generalizing Outside The Training Distribution.” (Chatgpt is a family member of a foundation model that can learn from vast Amounts of text to then Unders and Generate New Text.)

“In Many Ways, The Seed of Intelligence is the ability to Generalize Robustly,” Tolias Said. “The Ultimate Goal – The Holy Grail – To Generalize to Scenarios Outside Your Training Distribution.”

Mouse Movies

TO TRAIN THE NEW OA MODEL, THE RESEARCHERS FIRST RECORDED THE BRAIN ACTIVITY OF REAL MICE AS THEY WATCHED MOVIES-MADE-FOROPLE MOVIES. The Films Ideally Wold Approximate What the Mice Might See In Natural Settings.

“It’s very hard to sample a Realistic Movie for Mice, BECAUSE Nobody Makes Hollywood Movies for Mice,” Tolias Said. But action movies Came Close Enough.

MICE Have Low-Resolution Vision-Simile to Our Peripheral Vision-Meaning They Mainly See Movement Rather Than Details or Color. “Mice Like Movement, Which Strongly Activates Their Visual System, So We Showed Them Movies That Have A Lot of Action,” Tolias Said.

Over Many Short Viewing Sessions, The Researchers Recorded More Than 900 Minutes of Brain Activity from Eight Mice Watching Clips of Action-Packed Movies, Such as Mad Max. Cameras Monitored Their Eye Movements and Behavior.

The Researchers Used the AGGREGATED DATA TO TRAIN A CORE MODEL, WHICH COULD THIS CUSTOMIZED INTO DIGITAL TWIN OF ANY INDIVIDUAL MOUSE WITH BIT OF ADDITIONAL TRAINING.

PREDICATIONS ACCUREATE

These Digital Twins Were Aple To Closely Simulate The Neural Activity of Biological Counterparts in Response to a variety of new visual stimuli, including videos and static images. The Large Quantity of Aggregated Training Data Was Key to the Digital Twins’ Success, Tolias Said. “They were impressively accurate because their were trained on Such Large Datasets.”

THOUGH TRAINED ONLY ON NEUAL ACTIVITY, THE NEW MODELS COULD GENERALIZE TO OHER TYPES OF DATA.

The digital Twin of One Private Mouse was able to predict the anatomical locations and cell type of thousands of neurons in the visual court as well as the connections beteeen these neurons.

The Researchers Verified these Predictions Against High-Resolution, Electron Microscope Imaging of That Mouse’s Visual Cortex, Which Was Part of A Larger Project to Map the Structure and Function of the Mouse Visual Cortex In Unprecedenteded Detail. The Results of That Project, Known as MicronsWERE PUBLISHED SIMULTANEOUSLY IN Nature.

Opening The Black Box

BECAUSE A DIGITAL TWIN CAN FUNCTION LONG PAST THE LIFESPAN OF A MOUSE, SCIENTISTS COUND PERFORM A VIRTUALLY UNLIMITED NUMBER OF Experiments on Essentially The Same Animal. Experiments That Would Take Years Could Be Completed in Hours, and Millions of Experiments Could Run Simultaneously, Speeding Up Research Into How the Brain Processes Information and the Principles of Intelligence.

“We’re Trying to Open The Black Box, So to Speak, to Understand the Brain at the Level of Individual Neurons or Population of Neurons and How they work toGether to Encoda Information,” Tolias Said.

In FACT, THE NEW MODELS ARE ALREADY YIELDING NEW INSIGHTS. In Another Related Studyalso simultaneously published in NatureResearchers Used a Digital Twin To Discover How Neurons in the Visual Cortex Choose other Neurons with Which to Form Connections.

Scientists Had Known That Similar Neurons Tend To Form Connections, Like People Forming Friendships. The Digital Twin Revealed Which similaries mattered the most. Neurons Prefer To Connect With Neurons That Respond to the Same Stimulus – The Color Blue, Example – Over Neurons That Respond to the Same Area of ​​Visual Space.

“It’s Like Someone Selecting Friends Based on What They Like And Not Where They Are,” Tolias Said. “We Learned This More needs Rule of How the Brain Is Organized.”

The Researchers Plan to Extend Their Modeling Into other brain Areas and to Animals, Including Primates, with more Advanced Cognitive Capabilities.

“Eventually, I Believe It Will Be Possible to Build Digital Twins of At Least Parts of the Human Brain,” Tolias Said. “This is just the typ of the iceberg.”

Researchers from the University Göttingen and the Allen Institute for Brain Science Contributed to the Work.