RESEARCHERS have developed artificial intelligence which has the ability to ‘READ MINDS’, according to a new study.
Scientists from the Carnegie Mellon University (CMU) are now able to use brain activation patterns to identify complex thoughts and their roots.
The ‘mind reading’ technology shows that the brain forms complex thoughts through various sub-systems and are not word-based.
The research carried out by CMU’s Marcel Just offers fresh evidence that the basics of concept representation are universal and not specific to language.
Professor Just said: “One of the big advances of the human brain was the ability to combine individual concepts into complex thoughts, to think not just of ‘bananas,’ but ‘I like to eat bananas in evening with my friends’.
“We have finally developed a way to see thoughts of that complexity in the fMRI signal.
“The discovery of this correspondence between thoughts and brain activation patterns tells us what the thoughts are built of.”
The study revealed that the brains coding of complex sentences, such as “The witness shouted during the trial”, uses an alphabet of 42 meaning components and triggers activity in the brain relating to person, setting, size, social interaction and physical action of the items involved in a given sentence.
Each bit of information is processed in a different region of the brain which allowed the computer, which used machine learning algorithms, to predict what type of thoughts are being conjured.
The scientists used seven adult participants and asked them to think of 240 pre-agreed sentences.
By monitoring the brains using fMRI scans the machine was able to predict with 89 per cent accuracy what features were being left out of a sentence.
Prof Just added: “Our method overcomes the unfortunate property of fMRI to smear together the signals emanating from brain events that occur close together in time, like the reading of two successive words in a sentence.
“This advance makes it possible for the first time to decode thoughts containing several concepts. That’s what most human thoughts are composed of.”
“A next step might be to decode the general type of topic a person is thinking about, such as geology or skateboarding.
“We are on the way to making a map of all the types of knowledge in the brain.”