Biologically-Inspired Artificial Vision

We’re interested in reverse engineering biological visual systems. However, we would argue that any serious effort to reverse engineer a system should also include a component of forward engineering. For our purposes, this entails attempting to take principles we’ve learned from natural systems and build them into working artificial computer vision systems.

The brain is a massively parallel computer, far exceeding the power available in currently available computers. To make headway towards understanding how the brain works, we’re utilizing cutting-edge, high-performance computing techniques to bring us closer to the scale and complexity of biological neural systems.

In particular, we’re making extensive use of non-traditional supercomputing tools, such as modern graphics processing hardware (such as the IBM “Cell” Processor found in the Playstation 3, and high-end graphics cards), which can provide enormous speed-ups relative to conventional computers. As the scale of available computational power grows, we hope to be able to begin to rival the scale and complexity of naturally-occuring brains.

This work is a collaboration between our lab, and the DiCarlo Lab at MIT.

Highlights:

• See our new 16 GPU “Monster” System
• The Rowland Playstation 3 Cluster