:format(webp)/YXJ0aWNsZXMvaW1hZ2UvMjAyNS85LzIwMjUwOTI2LWdhZi11NTUtMTcyLmpwZw.webp?w=1920)
Scientists Train AI to Read Thoughts Through Brain Signals
Neurophysiologists introduced an AI model that converts brain signals into words without implants or speech. This marks the first step toward an interface capable of decoding inner speech.
A team of neurophysiologists has developed an artificial intelligence system capable of translating brain activity into meaningful words without using invasive technologies. The July study demonstrated that the model can read and interpret signals from an electroencephalogram (EEG) and reconstruct mentally articulated words.
The experiments tested three processing modes: spoken words, words heard by the subject, and words imagined silently without being spoken. The last mode, in which a participant mentally formed a word without vocalizing it, generated the most scientific interest.
The AI model showed significant progress compared to previous developments, doubling the recognition accuracy specifically for imagined articulation. Although the model is currently limited in speed, accuracy, and vocabulary, the ability to decode thoughts at such an early stage—without brain implants or external stimulation—is considered a breakthrough in the field of neural interfaces.
The algorithm analyzes EEG data to recognize patterns corresponding to specific words. Earlier technologies required deep neurointegration or worked with a limited set of pre-programmed commands. This new model shows potential for scalable and adaptable application based on individual brain characteristics.
While the technology is not yet intended for practical use, its creators believe that in the future such systems could become the basis for next-generation brain-computer interfaces. They may help restore communication in people with speech or motor impairments or those affected by paralysis.
Researchers emphasize that future efforts will focus on expanding the vocabulary, improving recognition accuracy, and adapting the model to various types of brain activity. Work is also ongoing to reduce false positives and increase resistance to background noise.
The development of such interfaces also requires attention to ethical considerations, including thought privacy and the potential for external mental control. The current project is strictly limited to voluntary participation and controlled experimental conditions.
The findings are viewed as an early yet crucial step toward creating technologies for direct communication between the brain and digital systems. The model proves that reading thoughts without physical intervention is becoming technically feasible, paving the way for future neural interfaces.
Do you have news that could become a sensation?
Or do you want to try yourself as an editor?
On altn.news , it's possible!
Share your materials, express your opinion, and test your skills as a journalist or editor.
It’s simple:
✅ Download the app:
✅ Register on the website.
✅ Create and publish your news.
Who knows, maybe your material will become the next big headline!
Start today on altn.news.
The editorial board is not responsible for the content and accuracy of material taken, sent or obtained from other sources. The publication of such materials is for informational purposes only and does not imply automatic endorsement or approval of their content.
