|Google's Coral allows companies to build products that are efficient, private, fast, and offline / Credits: Robson90 via Shutterstock|
Many artificial intelligence applications are currently being used in various functions across industries. They are programmed to accurately and efficiently help companies and consumers in their tasks. Traditionally, the data gathered from these applications are housed in centralized data centers where machine learning models could operate at speed. However, all of these are practically useless if they are not fast and secure enough.
To address this concern, Google launched a local AI platform called Coral, with on-device inferencing capabilities that allow companies to build products that are efficient, private, fast, and offline. While many of us might have heard about Coral, reports show that it’s a part of a fast-growing AI sector. Market analysts projected that more than 750 million edges AI chips and computers will be sold in 2020, rising to 1.5 billion by 2024.
“Coral is a platform of hardware and software components from Google that helps you build devices with local AI — providing hardware acceleration for neural networks ... right on the edge device,” Vikram Tank, product manager at Coral, said.
According to The Verge, an American technology news and media network that publishes news items, long-form feature stories, guidebooks, product reviews, and podcasts, Coral offers two main types of products to meet customers’ needs. First, the accelerators and dev boards are meant for prototyping new ideas while the other type is modules that are destined to power the AI brains of production devices like smart cameras and sensors. Also, there’s a library of AI models in Coral specifically compiled for its hardware.
However, Coral has its own limits because its Edge TPU-powered hardware only works with Google’s machine learning framework, TensorFlow. This is where their rivals are ahead of Coral. “Coral products process specifically for their platform [while] our products support all the major AI frameworks and models in the market,” a spokesperson for AI edge firm Kneron said.