In one aspect of vision, computers catch up to primate brain

Studies of mental functions, behaviors and the nervous system.

Moderators: Calilasseia, ADParker

In one aspect of vision, computers catch up to primate brain

#1  Postby kennyc » Dec 20, 2014 1:35 pm

In one aspect of vision, computers catch up to primate brain

For decades, neuroscientists have been trying to design computer networks that can mimic visual skills such as recognizing 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 MIT neuroscientists has found that one of the latest generation of these so-called "deep neural networks" matches 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, says James DiCarlo, a professor of neuroscience and head of MIT's Department of Brain and Cognitive Sciences and the senior author of a paper describing the study in the Dec. 11 issue of the journal PLoS Computational Biology.
"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," says DiCarlo, who is also a member of MIT's McGovern Institute for Brain Research.
This improved understanding of how the primate brain works could lead to better artificial intelligence and, someday, new ways to repair visual dysfunction, adds Charles Cadieu, a postdoc at the McGovern Institute and the paper's lead author.
Other authors are graduate students Ha Hong and Diego Ardila, research scientist Daniel Yamins, former MIT graduate student Nicolas Pinto, former MIT undergraduate Ethan Solomon, and research affiliate Najib Majaj.
Inspired by the brain
Scientists began building neural networks in the 1970s in hopes of mimicking the brain's ability to process visual information, recognize speech, and understand language.
For vision-based neural networks, scientists were 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.
"Each individual element is typically a very simple mathematical expression," Cadieu says. "But when you combine thousands and millions of these things together, you get very complicated transformations from the raw signals into representations that are very good for object recognition."
For this study, the researchers first measured the brain's object recognition ability. Led by Hong and Majaj, they implanted arrays of electrodes in the IT cortex as well as in area V4, a part of the visual system that feeds into the IT cortex. This allowed them to see the neural representation -- the population of neurons that respond -- for every object that the animals looked at.
The researchers could then compare this with representations created by the deep neural networks, which consist of a matrix of numbers produced by each computational element in the system. Each image produces a different array of numbers. The accuracy of the model is determined by whether it groups similar objects into similar clusters within the representation.
"Through each of these computational transformations, through each of these layers of networks, certain objects or images get closer together, while others get further apart," Cadieu says.
The best network was one that was developed by researchers at New York University, which classified objects as well as the macaque brain.
...


http://www.sciencedaily.com/releases/20 ... 141052.htm
Kenny A. Chaffin
Art Gallery - Photo Gallery - Writing&Poetry
"Strive on with Awareness" - Siddhartha Gautama
User avatar
kennyc
THREAD STARTER
 
Name: Kenny A. Chaffin
Posts: 8698
Male

Country: U.S.A.
United States (us)
Print view this post

Ads by Google


Re: In one aspect of vision, computers catch up to primate brain

#2  Postby DavidMcC » Dec 20, 2014 8:42 pm

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.

I believe there is a cortical region specialising in movement, so it may well be that that information is "cast aside" in the particuar region referred to here, but not in some other region. Thus, it is misleading to simply say some information is "cast aside", without qualifying that statement.
May The Voice be with you!
DavidMcC
 
Name: David McCulloch
Posts: 14913
Age: 67
Male

Country: United Kigdom
United Kingdom (uk)
Print view this post

Re: In one aspect of vision, computers catch up to primate brain

#3  Postby DavidMcC » Dec 24, 2014 12:26 pm

... Apparently, motion information is "cast aside" to area V5:
http://en.wikipedia.org/wiki/Motion_perception
...
Neuropsychology

The inability to perceive motion is called akinetopsia and it may be caused by a lesion to cortical area V5 in the extrastriate cortex. Neuropsychological studies of a patient who could not see motion, seeing the world in a series of static "frames" instead, suggested that visual area V5 in humans is homologous to motion processing area MT in primates.[1][2]


EDIT: Of course, motion information isn't relevant to object recognition, but that does not make it completely useless, and that is why it is not really thrown away.
May The Voice be with you!
DavidMcC
 
Name: David McCulloch
Posts: 14913
Age: 67
Male

Country: United Kigdom
United Kingdom (uk)
Print view this post


Return to Psychology & Neuroscience

Who is online

Users viewing this topic: No registered users and 1 guest