Training computers to understand the human brain

7th October 2012

Researchers have made an important breakthrough in teaching computers to understand human brain function.

Understanding how the brain categorises information through signs and language is a key part of developing computers that can "think" and "see" in the same way as we do. Researchers at the Tokyo Institute of Technology – along with co-workers in Yokohama, the USA, Italy and the United Kingdom – have taken a major step towards achieving this. Using functional magnetic resonance imaging (fMRI), they trained a computer to predict the semantic category of images previously viewed by five different people.

The participants were asked to look at pictures of animals and hand tools, together with an auditory or written (orthographic) description. They were asked to silently "label" each pictured object with certain properties, whilst undergoing a brain scan. The scans were then analysed using algorithms which identified patterns relating to the two separate semantic groups (animal or tool).

After "training" the algorithms in this way using auditory session data, the computer correctly identified the remaining scans 80-90% of the time. Similar results were obtained with the orthographic session data. Continued research in this area could lead to systems that allow people to speak through a computer simply by thinking about what they want to say.

Comments »