Take a fresh look at your lifestyle.

Maxim Integrated Camera Cube Reference Design Enables AI at the Edge

Maxim Integrated Products Inc. has launched the MAXREFDES178# camera cube reference design, which helps guide you artificial intelligence (AI) applications previously restricted to machines with large power and price budgets could be baked into space-constrained, battery-powered edge devices.

The MAXREFDES178# enables ultra-low-power internet of products (IoT) devices to implement hearing and vision and showcases the MAX78000 low-power microcontroller with neural network accelerator for video and audio inferences. The machine also contains the MAX32666 ultra-low power Bluetooth microcontroller and 2 MAX9867 audio CODECs.

The entire system is delivered within an ultra-compact form factor to show how AI applications for example facial identification and keyword recognition could be embedded in low-power, cost-sensitive applications for example wearables and IoT devices.

AI applications require intensive computations, usually performed in the cloud or in expensive, power-hungry processors that can only fit in applications with big power budgets such as self-driving cars. However the MAXREFDES178# camera cube helps guide you AI can survive a low-power budget, enabling applications that are time- and safety-critical to function on the smallest of batteries. The MAX78000’s AI accelerator slashes the power of AI inferences as much as 1,000x for vision and hearing applications, when compared with other embedded solutions. The AI inferences running around the MAXREFDES178# also show dramatic latency improvements, running more than 100x faster than you are on an embedded microcontroller.

The compact form factor from the camera cube at 1.6in x 1.7in x 1.5in (41mm x 44mm x 39mm) shows that AI could be implemented in wearables along with other space-constrained IoT applications. The MAX78000 solution is as much as 50 percent small compared to the next-smallest GPU-based processor and does not require other components like memories or complex power supplies to apply cost-effective AI inferences.

“The next big opportunity in AI is providing machine learning insights in the edge,” said Alan Descoins, CTO at Tryolabs. “The MAXREFDES178# shows how Maxim Integrated’s AI option would be a breakthrough in power, latency and size that may unlock the possibilities for AI in battery-powered designs.”

“Machine learning promises a great deal: that machines can make sense of what they see and hear like humans, as well as make more autonomous decisions. Until the MAX78000, the embedded world was left behind since you couldn’t implement AI at the edge in a power, cost and size constrained manner,” said Kris Ardis, executive director of the Micros, Security and Software Business Unit at Maxim Integrated. “Now the MAXREFDES178# helps guide you meaningful and powerful AI inferences could be run in the edge, on the smallest and many energy-conscious devices.”