Meet Google’s secret weapon for improving AI speeds—no cloud required

AI is only going to be a true game-changer if it can work its magic with significant speed and efficiency, something Google must have realized when it launched its Coral initiative. Coral’s solutions are designed to speed up AI applications by providing on-device assistance and removing the need for cloud-based connections.

A new report from The Verge looked at the potential impact of Coral, noting that the initiative is expected to play a key role in the healthcare and automotive industries.  

“Traditionally, data from [AI] devices was sent to large compute instances, housed in centralized data centers where machine learning models could operate at speed,” Vikram Tank, a product manager at Coral, told The Verge. “Coral is a platform of hardware and software components from Google that help you build devices with local AI—providing hardware acceleration for neural networks ... right on the edge device.”

Tank also offered medical devices as a key area where Coral’s solutions could make a difference when it comes to security. If a device sends images to the cloud, it means that hackers could potentially target that data—if the device can analyze images without the cloud, however, it removes that possibility.

Click the link below for the full story:

Michael Walter
Michael Walter, Managing Editor

Michael has more than 18 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.

Around the web

The tirzepatide shortage that first began in 2022 has been resolved. Drug companies distributing compounded versions of the popular drug now have two to three more months to distribute their remaining supply.

The 24 members of the House Task Force on AI—12 reps from each party—have posted a 253-page report detailing their bipartisan vision for encouraging innovation while minimizing risks. 

Merck sent Hansoh Pharma, a Chinese biopharmaceutical company, an upfront payment of $112 million to license a new investigational GLP-1 receptor agonist. There could be many more payments to come if certain milestones are met.