Researchers see through a mouse’s eyes by decoding brain signals

What was once the domain of science fiction and people claiming to have psychic powers is taking one step further into reality, as a team of researchers from the École Polytechnique Federal de Lausanne (EPFL) has successfully developed a machine learning algorithm that can decode the signals of a mouse’s brain. Reproduce images of what you see.

Before you share this new research with your Facebook group or email friends and family in a panic to tell them it’s time to put on their tinfoil hats, this hack doesn’t mean yet that shadowy governments can secretly read your mind – we’re still a long way from that reality. . But it is a fascinating next step that has the potential to pave the way for improvements in how we study human and animal brains, and how we understand the brain’s reactions to visual and other stimuli.

Reading and decoding the electrical activity that occurs in the brain is not a new area of ​​research. back in 2011, Scientists at the University of California, Berkeley revealed They were able to produce rudimentary video that eerily resembled the various movie trailers people were watching inside an MRI machine. In 2013, researchers from Radboud University Nijmegen in the Netherlands revealed that they were able to determine that What letter were the test subjects looking for in the alphabet based on their brain activity.

The research revealed by Switzerland’s EFPL today focused on mice, rather than humans. The rats were shown a black and white film clip from the 1960s of a man running up to a car and then opening its trunk. While the mice were watching the clip, the scientists measured and recorded their brain activity using Two methods: inserting electrode probes into their brains visual cortex area, as well Optical sensors of mice that have been genetically engineered so that neurons in their brains glow green when firing and transmitting information. This data was then used to train a new machine learning algorithm called CEBRA.

See through the mouse’s eyes by decoding brain signals

when next Apply to Capturing brain signals anew the mouse Watching the movie clip in black and white for the first time, the CEBRA algorithm was able to correctly identify certain frames with the mouse.s See as you watched. Because CEBRA was also trained in this segment, it was also Capable of creating near-perfect matching frames, but with occasional telltale distortions of AI-generated images.

Does this mean that a mouse with a brain probe can be used as a covert spying tool, with remote brain readings used to decode everything it sees? probably no. This search included a very specific (and short) clip of footage that the machine learning algorithm was also familiar with. In its current form, CEBRA also takes into account the activity of about 1% of neurons in the mouse brain, so there is certainly room for its accuracy and potential for improvement. The research is also not limited to decoding what the brain sees. A study published in the journal, nature, showing that CEBRA can also be used to “predict arm movements in primates,” and “reconstruct the positions of mice as they run freely around the ring.” It is potentially a more subtle way of looking at the brain, and understanding how all neural activity relates to what is being processed.

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top