Technology Review

Purdue University researchers are developing a chip designed to enable mobile processors to make use of deep learning, which could lead to mobile devices that can understand the content of images and video. The researchers have demonstrated that a co-processor connected to a conventional smartphone processor could help it run deep learning software. The software was able to detect faces or label parts of a street scene. Although the system is not as powerful as other systems, it shows how new forms of hardware could make it possible to use the power of deep learning more widely. "You probably have a collection of several thousand images that you never look at again, and we don't have a good technology to analyze all this content," says Purdue professor Eugenio Culurciello. To read further, please visit http://www.technologyreview.com/news/523181/an-ai-chip-to-help-computers-understand-images/.