Brain-Reading Tech Provides Revolutionary Brain-to-Machine Interface
A team of researchers from the University of Technology Sydney (UTS) in Australia have developed a revolutionary technology that can potentially transform thoughts into data that can be processed into words by a computer.
Studies involving translating brain signals into language are nothing new, but the Australian scientists have created “BrainGPT”, which tracks a brain’s activity and creates an algorithm of the user’s mind in order to produce a thought-to-text language.
The technology involves wearing a cap to record the electro-encephalogram (EEG) waves, the electrical activity of the human brain; the closer the electrodes are, the more accurate and high-quality the data received, producing more accurate results.
The interface’s current accuracy of the raw EEG is at 40%, but offers a wealth of possibilities for those unable to communicate, says Ching-Ten Lin, head of the project and a professor at the UTS School of Computer Science.
“The integration with large language models is also opening new frontiers in neuroscience and AI,” Lin mused, while explaining how non-invasive the tech is – referencing Elon Musk’s brain implant for his Neuralink network.
However, ensuring the software can more clearly process words from the signals is the primary goal of Lin’s team as they want to achieve 90%.
Image Credit: Source