For all their sophistication, computers still can't compete with nature's gift—a brain that sorts objects quickly and accurately enough so that people and primates can interpret what they see as it happens. Despite decades of development, computer vision systems still get bogged down by the massive amounts of data necessary just to identify the most basic images. Throw that same image into a different setting or change the lighting and artificial intelligence is even less of a match for good old gray matter.
These shortcomings become more pressing as demand grows for security systems that can recognize a known terrorist's face in a crowded airport and car safety mechanisms such as a sensor that can hit the brakes when it detects a pedestrian or another vehicle in the car's path. Seeking the way forward, Massachusetts Institute of Technology researchers are looking to advances in neuroscience for ways to improve artificial intelligence, and vice versa. The school's leading minds in both neural and computer sciences are pooling their research, mixing complex computational models of the brain with their work on image processing.
This cross-disciplinary approach began to yield fruit a year ago, when a group of researchers led by Tomaso Poggio, an investigator at M.I.T.'s McGovern Institute for Brain Research and a professor in the school's Department of Brain and Cognitive Sciences, used a brain-inspired computer model to interpret a series of photographs. Although the neurological model had been developed as a theoretical analysis of how certain visual pathways in the brain work, it turned out to be as good as, or even better than, the best existing computer vision systems at rapidly recognizing some complex scenes. Previously, when a computer was shown pictures of a horse, along with other animals standing in a forest and asked to identify the equine each time, it was swamped by all the data that might distinguish the horse from the other animals or the trees.
When the neurological model was used, it was the first time a computer model was able to reproduce human behavior on that kind of task, Poggio says, and it brought the researchers closer to understanding how the visual cortex recognizes objects and scenes.
Some car companies have for years been trying to develop computer systems that allow their vehicles to identify pedestrians and other vehicles amidst a crowded background and provide drivers with a warning if they get too close. This type of recognition is very easy for humans, Poggio says, but "we're not conscious of what goes on in our head[s] when we do this."
When a person is shown a picture, even for just a fraction of a second, the brain's visual cortex recognizes what it sees immediately. The visual cortex is a large part of the brain's processing system and one of the most complex. Poggio says that understanding how it works could be a significant step toward knowing how the whole brain operates. "Vision is just a proxy for intelligence," he says. The human brain is much more aware of how it solves complex problems such as playing chess or solving algebra equations, which is why computer programmers have had so much success building machines that emulate this type of activity.
Thus far, Poggio's research has modeled "feedforward" vision, which occurs when an image is first presented to the eye. He and his colleagues are now looking to develop new models that help them better understand how the brain works once the eye begins to scan the scene portrayed in an image and interpret spatial relationships among objects in the scene. The hope is that this will ultimately lead to computer software that can do the same thing and eventually explain not only rapid cognition by humans but also other aspects of our visual intelligence. Keep your eyes peeled.
See what we're tweeting about
6 Comments
Add Comment"For all their sophistication, computers still can't compete with nature's gift"
Reply | Report Abuse | Link to this"Nature's" gift?? I didn't realize "nature" gave gifts? Who is "nature" and since when did nature have a will, especially to give a gift? Nature is quite the gift-giver, with all these great gifts of hurricanes that are destroying the very thing it supposedly "gave". I'm pretty sure by "nature" you meant "random happenstance", which is much more accurate under the precepts of evolution. Otherwise, you'd have to admit an intelligent will gave us our brains. And that has certainly become a no-no for the science community. Too bad.
part 1 of 2
Reply | Report Abuse | Link to thisAt least the most important paradigm of research into artificial intelligence is recognized: A computer simulation of the brain's working is limited to our understanding of the brain.
If we put our knowlege gleaned from neurology into a computer program, and that program falls short of the capabilities of our brain, it does not show limitations of the computer, but limitations of our own knowledge about he workings of the brain.
Computers (up to now) perform pattern analysis, which is a tremendously complex task.
However, the natural brain of any crerature with a brain [or any precursor thereof, down to the most primitive single cell capable of directed movement] "merely" performs pattern recognition.
(see next part)
(part 2 of 2)
Reply | Report Abuse | Link to thisA duck sees a fox and takes to its wings: This is NOT the result of calculations faster than those of the most advanced supercomputer. For the survival of ducks it is mandatory, and sufficient, to recognize a pattern.
In the kingdom of animals patterns are not analyzed, but realized, collected and recognized.
Humans did not abrogate the capalility of pattern recognition, which has ben essential for survival (i.e., has been selected from a series of pertainigg mutations ) a billion of years ago or earlier.
As long as the quest for artificial intelligence is restricted to our knowledge of conscious reasoning it will never come near to the capabilities of the human brain, nor that of a humble duck.
IMO for visual pattern recognition we don't need to study human brain, other creatures with much more simpler brain are able to recognize things, too.
Reply | Report Abuse | Link to thisWould it be possible to simulate evolution of brain in computers? Starting with some simple neural systems, putting them into virtual world with rules for reproduction, mutation..
The idea is that maybe computers could simulate brain behavior better in "their way" (not by creating exact copy of processes in biological brain) - evolution would figure that out
The only difference between God and us : Gods computer is larger in one sense and smaller in another(nano science); and He can get from point a to b quicker than we can(instantaneous movement about the universe(via bending space rather than traveling thru it-just worm holing around his estate).
Reply | Report Abuse | Link to thiser. Apple has Face recognition, no? So...why can't robots detect faces through this technology? [And Apple's Face recognition is good from my experience]
Reply | Report Abuse | Link to this