MRI scans and AI to decode what we think? This study has answers

Is mind reading possible? An age-old question with multiple unproven answers. Those who study psychology often claim that they can understand what the other person is saying as they study mental processes, brain functions, and behaviour, but even they can't be 100 per cent accurate.

A study, published in the journal Nature Neuroscience, attempts to address it as scientists have said that they have come up with a way to decode a stream of words in the brain using MRI scans and artificial intelligence.

The study titled — "Semantic reconstruction of continuous language from non-invasive brain recordings" — noted that the system won't replicate each word but it reconstructs the brief of what a person hears or imagines.

Add WION as a Preferred Source

Alexander Huth, a co-author of the study and an assistant professor of neuroscience and computer science at The University of Texas at Austin, said: "It's getting at the ideas behind the words, the semantics, the meaning."

ALSO READ |Study finds patients in coma had 'conscious-like' brain activity before death

Of course, the system won't be able to read minds as it only works when a participant is actively cooperating with scientists.

In the study, published on May 1, it was mentioned that a system of a non-invasive decoder, whichreconstructs continuous language from cortical semantic representations recorded using functional MRI, has been introduced.

"Given novel brain recordings, this decoder generates intelligible word sequences that recover the meaning of perceived speech, imagined speech and even silent videos, demonstrating that a single decoder can be applied to a range of tasks," part of the study mentioned.

The authors have also stated that they have tested the decoder across the cortex and found that continuous language can be separately decoded from multiple regions.

ALSO READ |Fur of Costa Rican sloths may harbour antibiotic-producing bacteria: Study

They added that we tested whether successful decoding requires subject cooperation and found that subject cooperation is required both to train and to apply the decoder — as brain–computer interfaces should respect mental privacy.

They said, "Our findings demonstrate the viability of non-invasive language brain–computer interfaces."

To derive the result, the researchers trained decoders for three subjects. They evaluated each subject’s decoder on separate, single-trial brain responses that were recorded while the subject listened to novel test stories that were not used for model training.

The researchers said that as their decoder represents language using semantic features rather than motor or auditory features, its predictions should capture the meaning of the stimuli.

"Results show that the decoded word sequences captured not only the meaning of the stimuli but often even exact words and phrases, demonstrating that fine-grained semantic information can be recovered," the study mentioned.

WATCH WION LIVE HERE

You can now write for wionews.com and be a part of the community. Share your stories and opinions with us here.