New Platform Aims To Make AI Edge Device Development Easy
On Thursday Seattle, Wash.-based Xnor.ai announced the launch of AI2GO, a brand-new "self-serve" platform that the company says makes it easy for developers without an artificial intelligence (AI) background to build smart edge-based products for Internet of Things (IoT) solutions and other uses that require the smaller footprint and quicker processing time that an edge computing architecture can offer.
"AI2GO gives developers access to hundreds of deep learning models, which can be deployed on resource-constrained devices such as car dash cams and home security cameras with a few lines of code," the company explained in its announcement of the new release.
According to Xnor.ai, the new platform is basically plug-and-play when it comes to these models -- all of which are "pre-tuned," "fully trained" and "ready to go." A list of hardware platforms for the models is available here.
Xnor.ai founder Ali Farhadi explained in an e-mailed statement why he feels this new release is so revolutionary: "Building AI is hard. Building AI for the edge is even harder. You don't see many products running AI locally and it's not because the technology doesn't exist; it's because it's really difficult to get it in production. AI2GO will change all that because now any developer can add AI into their edge device with a couple lines of code."
While this first version will only work with the pre-supplied models, Farhadi said next version will allow developers to upload their own models, adding even more functionality.
The AI2GO SDK includes not only the models but benchmarking tools, samples (for Python and C) and related documentation. The SDK can be downloaded here.
Becky Nagel is the vice president of Web & Digital Strategy for 1105's Converge360 Group, where she oversees the front-end Web team and deals with all aspects of digital strategy. She also serves as executive editor of the group's media Web sites, and you'll even find her byline on PureAI.com, the group's newest site for enterprise developers working with AI. She recently gave a talk at a leading technical publishers conference about how changes in Web technology may impact publishers' bottom lines. Follow her on twitter @beckynagel.