Scientists Develop AI that can turn Brain Thoughts into text

Mind reading may be possible with true facts; a team of US Researchers develops an AI algorithm that turns Brain thoughts into text. Currently, a developed AI-based system detects neural patterns when someone speaks aloud. The experts say the system will help people who are unable to speak or suffering from locked-in syndrome.

“We are not there yet but we think this could be the basis of a speech prosthesis,” said Dr Joseph Makin, co-author of the research from the University of California, San Francisco. In Nature Neuroscience Journal published by Researchers they also share the process of development of AI algorithm.

The participants were asked to read aloud, their neural patterns were tracked and fed into Machine Learning Algorithm. This machine-learning algorithm converts brain activity into logical representation (numbers). In order to verify the result, Sounds predicted from small chunks compared to actual sounds by the system.

The system accuracy varies for one participant each sentence to 3%; which is higher than the error rate of human transcribers. The AI-based algorithm only handles only a small number of sentences. Researchers also find that the system requires less training data for the final user.

Reasearchers Makin and colleagues writes in journal that they depends on brain activity for data. In order to get brain data electrode array are need to implanted into the brain, which no one easily accept. The researchers team is still working on the AI algorithm that turns brain thoughts into text for improvements. What do you think about this research, comment down below.

More from this stream

Recomended