Machines can read the thoughts of trained humans better
Keystone-SDA
Humans can learn to share their thoughts with machines. In a new study, researchers from the University of Geneva have shown that so-called brain-machine interfaces can read the thoughts of specially trained people better than those of untrained people.
+ Get the most important news from Switzerland in your inbox
The researchers hope that this will enable a new form of communication for people who can no longer speak after a stroke, for example, as the University of Geneva announced on Monday.
For the study, the researchers attached electrodes to the scalp of 15 volunteers in order to detect and record voltage fluctuations in the brain. Wired up in this way, the volunteers had to imagine the syllables “fo” and “gi”, i.e. only pronounce them internally.
More
More
Explainer: Why US health funding cuts are rattling Swiss science
The brain activity was analysed in real time. The participants received visual feedback on a screen that showed how well the system had understood the syllables. The clearer their perception, the more a display filled up. They trained in this way for five days.
Importance of training underestimated
Despite individual differences in learning progress, the volunteers became significantly better at communicating the two syllables with the machine, as the researchers showed in the study published in the journal Communications Biology. In contrast, a control group with irregular visual feedback showed no comparable progress.
According to the university, this research emphasises the previously underestimated importance of training when using brain-machine interfaces.
Translated from German by DeepL/jdp
This news story has been written and carefully fact-checked by an external editorial team. At SWI swissinfo.ch we select the most relevant news for an international audience and use automatic translation tools such as DeepL to translate it into English. Providing you with automatically translated news gives us the time to write more in-depth articles.
If you want to know more about how we work, have a look here, if you want to learn more about how we use technology, click here, and if you have feedback on this news story please write to english@swissinfo.ch.
