Computer matches primate brain in object recognition

MIT scientists have found that some computer programmes can identify objects in images just as well as the primate brain.
For decades, neuroscientists have been trying to design computer networks that can mimic visual skills such as recognising objects, which the human brain does very accurately and quickly.
Until now, no computer model has been able to match the primate brain at visual object recognition during a brief glance.
However, a new study from Massachusetts Institute of Technology neuroscientists has found that one of the latest generation of these so-called "deep neural networks" matches the primate brain.
The study found that a neural network developed by researchers at New York University classified objects as well as the primate brain.

Because these networks are based on neuroscientists' current understanding of how the brain performs object recognition, the success of the latest networks suggest that neuroscientists have a fairly accurate grasp of how object recognition works, said James DiCarlo, a professor of neuroscience and head of MIT's Department of Brain and Cognitive Sciences.

"The fact that the models predict the neural responses and the distances of objects in neural population space shows that these models encapsulate our current best understanding as to what is going on in this previously mysterious portion of the brain," said DiCarlo, senior author of the study in the journal PLoS Computational Biology.

This improved understanding of how the primate brain works could lead to better artificial intelligence and, someday, new ways to repair visual dysfunction, added Charles Cadieu, a postdoc at the McGovern Institute and the paper's lead author.
For vision-based neural networks, scientists have been inspired by the hierarchical representation of visual information in the brain.
As visual input flows from the retina into primary visual cortex and then inferotemporal (IT) cortex, it is processed at each level and becomes more specific until objects can be identified.
To mimic this, neural network designers create several layers of computation in their models. Each level performs a mathematical operation, such as a linear dot product.

At each level, the representations of the visual object become more and more complex, and unneeded information, such as an object's location or movement, is cast aside.