Maxim Integrated was named the winner of the most innovative product in the AI category of the Best in Sensors Awards 2020 for its MAX 78000 Neural Network Accelerator Chip. Entries were judged and winners selected on the basis of value to the marketplace, uniqueness of the design, and the impact (i.e., the “bigness” of the problems solved or issues addressed).
Introduced in September, the MAX78000 low-power neural network accelerated microcontroller from Maxim Integrated moves artificial intelligence (AI) to the edge without performance compromises in battery-powered Internet of Things (IoT) devices. Maxim says that executing AI inferences at less that 1/100th the energy of software solutions dramatically improves run-time for battery-powered AI applications, while enabling complex new AI use cases previously considered impossible.
AI technology allows machines to see and hear, making sense of the world in ways that were previously impractical. In the past, bringing AI inferences to the edge meant gathering data from sensors, cameras and microphones, sending that data to the cloud to execute an inference, then sending an answer back to the edge. This architecture works but is very challenging for edge applications due to poor latency and energy performance.
As an alternative, low-power microcontrollers can be used to implement simple neural networks; however, latency suffers and only simple tasks can be run at the edge. By integrating a dedicated neural network accelerator with a pair of microcontroller cores, the MAX78000 overcomes these limitations, enabling machines to see and hear complex patterns with local, low-power AI processing that executes in real-time. Applications such as machine vision, audio and facial recognition can be made more efficient since the MAX78000 can execute inferences at less than 1/100th energy required by a microcontroller, according to Maxim.
At the heart of the MAX78000 is specialized hardware designed to minimize the energy consumption and latency of convolutional neural networks (CNN). According to Maxim, the hardware runs with minimal intervention from any microcontroller core, making operation extremely streamlined. Energy and time are only used for the mathematical operations that implement a CNN. To get data from the external world into the CNN engine efficiently, customers can use one of the two integrated microcontroller cores: the ultra-low power ARM™ Cortex™-M4 core, or the even lower power RISC-V core.
AI development can be challenging, and Maxim Integrated provides comprehensive tools for a more seamless evaluation and development experience. The MAX78000EVKIT# includes audio and camera inputs, and out-of-the-box running demos for large vocabulary keyword spotting and facial recognition. Complete documentation helps engineers train networks for the MAX78000 in the tools they are used to using.
“This new product wins hands-down for its bigness because it can be used in billions of battery-powered products in the Internet of Things space to prevent AI compute work from being done in the cloud or data center and relies on 1% of the power of software-based solutions,” said Judge Matt Hamblen, Editor at FierceElectronics. “The technology appears to be unique among products that offer AI at the edge because of the design with an Arm Cortex processor as well as a RISC-V coprocessor along with a neural network accelerator.”
For full list of finalists in the Best of Sensors 2020 Awards
https://www.fierceelectronics.com/sensors/best-sensors-awards-2020-finalists-announced