Using machine learning algorithm, US researchers have developed a novel brain imaging technology that can ‘read minds’ and identify complex thoughts with 87 per cent accuracy.
The findings indicate that the mind’s building blocks for constructing complex thoughts are formed by the brain’s various sub-systems and are not word-based. By measuring the activation in each brain system, the new technology can tell us what types of thoughts are being contemplated.
“We have finally developed a way to see thoughts of such complexity in the fMRI signal. The discovery of this correspondence between thoughts and brain activation patterns tells us what the thoughts are built of,” says Marcel Just, Professor at Carnegie Mellon University, Pennsylvania.
The study is published in the journal Human Brain Mapping. The model was able to predict the features of the left-out sentence, with 87 per cent accuracy, despite never being exposed to its activation before.
“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,” Just explains.
“This advance makes it possible for the first time to decode thoughts containing several concepts,” the professor adds.