Computer-based "deep neural network" as good as primates at visual object recognition

Computers aren't best suited to visual object recognition. Our brains are hardwired to quickly see and match patterns in everything, with great leaps of intuition, while the processing center of a computer is more akin to a very powerful calculator. But that hasn't stopped neuroscientists and computer scientists from trying over the past 40 years to design computer networks that mimic our visual skills. Recent advances in computing power and deep learning algorithms have accelerated that process to the point where a group of MIT neuroscientists has found a network design that compares favorably to the brain of our primate cousins... Continue Reading Computer-based "deep neural network" as good as primates at visual object recognition



Section: Science



Tags: Brain, Computers, Learning, MIT, Object Recognition



Related Articles:

• Rat receives functioning artificial cerebellum


• Researchers simulate schizophrenia in a computer


• New object recognition algorithm learns on the fly


• New technique brings computer model of the brain a step closer


• “Seeing” NeuFlow supercomputer based on the human visual system


• New technique reduces processing power needed for facial recognition

from Gizmag Emerging Technology Magazine http://ift.tt/1v7I43D

via IFTTT