CMU computers seek where thoughts originate

| Friday, Jan. 4, 2008

Computers are reading minds at Carnegie Mellon University.

In a small two-year study, computer scientists and cognitive neuroscientists teamed up to teach computers to recognize patterns in brain activity and identify objects that people are looking at.

Scientists call it the first step toward identifying where people's thoughts originate, while ethicists see it as a sign of the need for new public policy.

"Many people were skeptical that this was doable," said neuroscientist Marcel Just, who directs Carnegie Mellon's Center for Cognitive Brain Imaging, and co-wrote the research article, which was published Wednesday evening in the Public Library of Science's online journal. "So we were overjoyed when it worked. Really, it is such a big thing."

A dozen volunteers were shown line drawings of five different types of buildings and five different kinds of tools while their brain activity was monitored by functional magnetic resonance imaging -- or fMRI -- which measures changes in blood flow.

Computers then analyzed the fMRI images -- which are taken 60 times a minute -- checking 20,000 locations on each image for changes in activity. Patterns emerged, and the computers were able to "learn" which patterns of brain activity were associated with specific images and determine not only whether the person was looking at a picture of a building or a tool, but which tool.

Even more significant, the patterns established with the fMRI images were used to identify which of the objects was being viewed by a different set of people. This means that people generally think the same way, and a computer program could conceivably be written to read the minds of most people, Just said.

"This is really a big scientific first that the brain's representation of objects is similar across different people," Just said.

Hank Greely, a Stanford University law professor and chairman of the university's Center for Biomedical Ethics, said the research could be used for good causes -- such as helping a quadriplegic communicate -- or bad, such as by a totalitarian government wanting to determine its citizens' allegiance.

"We're living in the middle of a revolution, the early parts of a revolution in our understanding of the brain," said Greely, who did not participate in the research. "The extent to which we understand how our brains work ... is going to transform society.

"The time to begin thinking and talking and debating how to use this technology is now."

Just said there are many potential uses for the research, ranging from determining where a criminal has hidden a weapon to teaching a person a complex skill, then scanning their brain to see if they've learned it. He is especially excited about its potential as a tool for autism research.

"We could find out which of the brain areas activate differently in a person with autism," Just said. "I suspect that when thinking about a hammer, it won't be much different, but with a concept like grief, it would be."

Dr. Nancy Minshew, director of the Center for Excellence in Autism Research at the University of Pittsburgh, praised the work, and agreed it could be a powerful tool.

"The brain is very complex, and in autistic people it's not just one spot that's not working or even a few spots," she said. "It's about how all these areas are working in concert together. This research could show us the disconnects."

Subscribe today! Click here for our subscription offers.


Show commenting policy