Machine Vision and Neuroscience are the fields that have lots of potential to make break through in the Artificial Intellegence. Neuroscience is a branch of biology that deals with understanding how brains function. On the other hand, Machine Vision is a computer science field that deals with creating a machine that can see like humans. Now you might feel a bit odd but the way machine interprets an image is completely different than the way human’s interpret the picture.

Though these two field are way apart, the knowledge and understanding accumulated in these fields can work together to make a machine that can interpret images the way human do. Scientist around the globe are trying the crack this problem and now MIT and Harvard have demonstrated way of making an artificial visual system in a much better way. In order to deploy their system, they have assembled stacks of  high-end Graphics Processing Units (GPUs) to build a computer which performs at high speeds, allowing complex computation to take only few seconds.

How they did it: Harnessing the processing power of dozens of high-performance NVIDIA graphics cards and PlayStation 3s gaming devices, the team designed a high-throughput screening process to tease out the best parameters for visual object recognition tasks. The resulting model outperformed a crop of state-of-the-art vision systems across a range of tests — more accurately identifying a range of objects on random natural backgrounds with variation in position, scale, and rotation. Had the team used conventional computational tools, the one-week screening phase would have taken over two years to complete.

The speed of the computer matters in such technology because the machine involves solving complex mathematical equations at a very higher rate to even identify a simple objects. Below is the video that demonstrated the technology and the system.

Funding: National Institutes of Health, McKnight Endowment for Neuroscience, Jerry and Marge Burnett, the McGovern Institute for Brain Research at MIT, and the Rowland Institute at Harvard. Hardware support provided by the NVIDIA Corporation.

Source of News : MIT

Image Source :

http://web.mit.edu/~bcs/images/newsevents/eye_brain_sm.jpg