The human brain’s ability to recognize objects is remarkable. If you see under unusual lighting or from unexpected directions, there’s a good chance that your brain will still recognize it, and it’s considered an anamoly when it doesn’t. This robust and precise object recognition is a holy grail for artificial intelligence developers. How our brains do this, however, is still a mystery. Here’s an interesting article from MIT on how researchers may be on to something powerful in the computer vision space.
Think of feedforward DCNNs, and the portion of the visual system that first attempts to capture objects, as a subway line that runs forward through a series of stations. The extra, recurrent brain networks are instead like the streets above, interconnected and not unidirectional. Because it only takes about 200 ms for the brain to recognize an object quite accurately, it was unclear if these recurrent interconnections in the brain had any role at all in core object recognition.
Perhaps those recurrent connections are only in place to keep the visual system in tune over long periods of time. For example, the return gutters of the streets help slowly clear it of water and trash, but are not strictly needed to quickly move people from one end of town to the other. DiCarlo, along with lead author and CBMM postdoc Kohitij Kar, set out to test whether a subtle role of recurrent operations in rapid visual object recognition was being overlooked.