Xnor.ai, a Seattle-based leading provider of efficient Artificial Intelligence technology for edge devices, has developed a small, solar-powered computer chip which is capable to run Machine Learning algorithms, without requiring a battery or other power sources. The Xnor.ai’s chip equipped with a camera, which can identify visual objects. The always-on device utilizes edge computing that means data captured by the camera never vanished from the device.
The solar-powered computer chip can also be attached to a battery or other source of power, but a solar panel was used to manifest unique use cases which can evolve when an AI system generates reliable outcomes and utilize 5mJ of energy for every inference instance. Founded in 3-years back in 2016, Xnor.ai Co-founder Ali Farhadi said that the company runs under a business model that includes licensing its proprietary software to users in exchange for the monthly or yearly fee. The solar-powered chip is not available in the marketplace; it’s just showcasing to get current and potential future customers of Xnor.ai. Farhadi further noted that by outfitting the basic electronic devices with chips like the company has built and turned them into AI workhorses, more of data could get crunched and making the chips’ core algorithms more sophisticated. As having more smaller and cheaper computing devices, it can do more Machine Learning tasks with saving energy.
Xnor.ai called its chip run state-of-the-art Machine Learning models by utilizing a cheap, obtainable solar cell as a power source. The company also said that its chip can send out images and data recorded by the built-in camera to other devices without a connection of Internet. Further, its technology enables computer processors to evaluate data in a way that utilizes relatively low amounts of power.