Mind reading is a science fiction thing that scientist intend to bring to the realm of reality with a new study suggesting that there could be a possibility to do so using a combination of artificial intelligence, machine learning and brain imaging.
Scientists at Carnegie Mellon University have come up with a novel brain imaging technology using machine learning algorithm, to “read minds” and identify complex thoughts with 87 per cent accuracy. This is a huge development as scientists claim they are able to measure the activation in each brain system and tell us what types of thoughts are being contemplated.
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. Scientist involved with the study published in journal Human Brain Mapping that they have finally developed a way to see thoughts of such complexity in the fMRI signal. The discovery also gives scientists an understanding of what the thoughts are built of.
Researchers selected seven participants for their study and used a computational model to assess how the brain activation patterns for 239 sentences corresponded to the neurally plausible semantic features that characterised each sentence. Scientists were able to decode the features of the 240th left-out sentence. They went through leaving out each of the 240 sentences in turn, in what is called cross-validation.
The model was able to predict the features of the left-out sentence, with 87 percent accuracy, despite never being exposed to its activation before.
The novel brain imaging technology 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 technology enables scientists to decode thoughts containing several concepts.