New self-service platform helps developers apply AI at the edge
In the past AI has mostly depended on expensive solutions running in the cloud, restricting its use to a relatively small number of companies.
But with the growth of the IoT and ever greater volumes of information that need to be processed fast, there's more demand for AI at the edge. Xnor is launching a new self-service platform called AI2GO, that enables developers, device creators and companies to build smart, edge-based solutions without needing training or background in AI.
The platform offers hundreds of fully-trained edge AI models, so developers no longer need to worry about data collection, annotation, training, model architecture or performance optimization. They can simply download the complete solution and be ready to go.
In the coming months, the AI2GO platform will provide enterprise customers access to fully optimized models along with additional custom features including automated training and re-training, and performance optimization for large-scale development teams.
"By providing access to deep learning that can readily run on-device, we believe we afford all companies regardless of team, budget or hardware the opportunity to participate in this new era of AI innovation. AI2GO enables this vision through a platform of a large number of models, running on a large number of devices, that are able to operate under a large number of constraints," says Ali Farhadi, co-founder and CXO at Xnor.
To use the platform the developer selects their preferred hardware (Raspberry Pi, Linux, Ambarella, etc.), then chooses an AI use case. Because AI2GO models are designed to run in resource-constrained environments, Xnor provides the user with the opportunity to tune their model for latency and memory footprint in order to fit with a given set of constraints. The user can then download an Xnor Bundle (XB), a module containing a deep learning model and an inference engine. Xnor also provides an accompanying SDK that includes access to code samples, demo applications, benchmarking tools and technical documentation.