Author: Jennifer Michalowski | McGovern Institute for Brain Research<\/p>\n
The human brain seems to care a lot about faces. It\u2019s dedicated a specific area to identifying them, and the neurons there are so good at their job that most of us can readily recognize thousands of individuals. With artificial intelligence, computers can now recognize faces with a similar efficiency \u2014 and neuroscientists at MIT\u2019s McGovern Institute for Brain Research have found that a computational network trained to identify faces and other objects discovers a surprisingly brain-like strategy to sort them all out.<\/p>\n
The finding, reported March 16 in Science Advances<\/em><\/a>, suggests that the millions of years of evolution that have shaped circuits in the human brain have optimized our system for facial recognition.<\/p>\n \u201cThe human brain\u2019s solution is to segregate the processing of faces from the processing of objects,\u201d explains Katharina Dobs, who led the study as a postdoc in the lab of McGovern investigator Nancy Kanwisher<\/a>,\u00a0the Walter A. Rosenblith Professor of Cognitive Neuroscience at MIT. The artificial network that she trained did the same. \u201cAnd that\u2019s the same solution that we hypothesize any system that\u2019s trained to recognize faces and to categorize objects would find,\u201d she adds.<\/p>\n \u201cThese two completely different systems have figured out what a \u2014 if not the \u2014 good solution is. And that feels very profound,\u201d says Kanwisher.<\/p>\n Functionally specific brain regions<\/strong><\/p>\n More than 20 years ago, Kanwisher and her colleagues discovered a small spot in the brain\u2019s temporal lobe that responds specifically to faces. This region, which they named the fusiform face area, is one of many brain regions Kanwisher and others have found that are dedicated to specific tasks, such as the detection of written words, the perception of vocal songs, and understanding language.<\/p>\n Kanwisher says that as she has explored how the human brain is organized, she has always been curious about the reasons for that organization. Does the brain really need special machinery for facial recognition and other functions? \u201c\u2018Why questions\u2019 are very difficult in science,\u201d she says. But with a sophisticated type of machine learning called a deep neural network, her team could at least find out how a different system would handle a similar task.<\/p>\n Dobs, who is now a research group leader at Justus Liebig University Giessen in Germany, assembled hundreds of thousands of images with which to train a deep neural network in face and object recognition. The collection included the faces of more than 1,700 different people and hundreds of different kinds of objects, from chairs to cheeseburgers. All of these were presented to the network, with no clues about which was which. \u201cWe never told the system that some of those are faces, and some of those are objects. So it\u2019s basically just one big task,\u201d Dobs says. \u201cIt needs to recognize a face identity, as well as a bike or a pen.\u201d<\/p>\n As the program learned to identify the objects and faces, it organized itself into an information-processing network with that included units specifically dedicated to face recognition. Like the brain, this specialization occurred during the later stages of image processing. In both the brain and the artificial network, early steps in facial recognition involve more general vision processing machinery, and final stages rely on face-dedicated components.<\/p>\n It\u2019s not known how face-processing machinery arises in a developing brain, but based on their findings, Kanwisher and Dobs say networks don\u2019t necessarily require an innate face-processing mechanism to acquire that specialization. \u201cWe didn\u2019t build anything face-ish into our network,\u201d Kanwisher says. \u201cThe networks managed to segregate themselves without being given a face-specific nudge.\u201d<\/p>\n Kanwisher says it was thrilling seeing the deep neural network segregate itself into separate parts for face and object recognition. \u201cThat\u2019s what we\u2019ve been looking at in the brain for 20-some years,\u201d she says. \u201cWhy do we have a separate system for face recognition in the brain? This tells me it is because that is what an optimized solution looks like.\u201d<\/p>\n Now, she is eager to use deep neural nets to ask similar questions about why other brain functions are organized the way they are. \u201cWe have a new way to ask why the brain is organized the way it is,\u201d she says. \u201cHow much of the structure we see in human brains will arise spontaneously by training networks to do comparable tasks?\u201d<\/p>\n<\/div>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"