The project is to implement artificial neural networks using optics rather than electronics. Optical neural networks would enable us to enhance both the power efficiency and speed of neural networks by several orders of magnitude. The specific aim is to develop a conceptually novel deep optics neural network system for computer vision. This system will allow an optical neural network to "see" and interpret objects directly, bypassing the processing bottleneck associate with converting an image into an electronic form. Such a system will have ultra-low latency and find applications in autonomous vehicles, remote sensing and intelligent robotics.
See further particulars at the web site below. |