Primates visually recognise and determine the category of an object even at a brief glance, and to date, this behaviour has been unmatched by artificial systems. A study publishing this week in PLOS Computational Biology has found that the latest artificial "deep neural network" performs as well as the primate brain at object recognition.
Charles Cadieu and colleagues from MIT measured the brain's object recognition ability by implanting arrays of electrodes in the inferior temporal cortex of macaques. This allowed the researchers to see the neural representation -- the population of neurons that respond -- for every object that the animals looked at.
When comparing these results with representations created by the deep neural networks, the accuracy of the model was determined by whether it grouped similar objects into similar clusters within the representation.
This improved understanding of how the primate brain works could lead to better artificial intelligence and provide insight into understanding primate visual processing.
"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," say the authors.
###
All works published in PLOS Computational Biology are Open Access, which means that all content is immediately and freely available. Use this URL in your coverage to provide readers access to the paper upon publication: http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1003963
Contact: Charles Cadieu
Address: Massachusetts Institute of Technology
Brain and Cognitive Sciences
77 Massachusetts Ave, 46-6161
Cambridge, MA 02139
UNITED STATES
Phone: 15162200119
Email: cadieu@mit.edu
Citation: Cadieu CF, Hong H, Yamins DLK, Pinto N, Ardila D, et al. (2014) Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition. PLoS Comput Biol 10(12): e1003963. doi:10.1371/journal.pcbi.1003963
Funding: This work was supported by the U.S. National Eye Institute (NIH NEI: 5R01EY014970-09), the National Science Foundation (NSF: 0964269), and the Defense Advanced Research Projects Agency (DARPA: HR0011-10-C-0032). CFC was supported by the U.S. National Eye Institute (NIH: F32 EY022845-01). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Competing Interests: The authors have declared that no competing interests exist.
About PLOS Computational Biology
PLOS Computational Biology (http://www.ploscompbiol.org) features works of exceptional significance that further our understanding of living systems at all scales through the application of computational methods. All works published in PLOS Computational Biology are Open Access. All content is immediately available and subject only to the condition that the original authorship and source are properly attributed. Copyright is retained. For more information follow @PLOSCompBiol on Twitter or contact ploscompbiol@plos.org.
About PLOS
PLOS is a nonprofit publisher and advocacy organization founded to accelerate progress in science and medicine by leading a transformation in research communication. For more information, visit http://www.plos.org.
Journal
PLoS Computational Biology