Maxim Integrated MAX78000 neural network accelerated microcontroller

The MAX78000 low-power neural network accelerated microcontroller, from Maxim Integrated Products, is designed to move AI to the edge without performance compromises in battery-powered IoT devices. By executing AI inferences using less than one-hundredth of the energy required by a microcontroller, the product should improve run-time for battery-powered AI applications while enabling complex AI use cases previously considered impossible. It is also said to execute inferences 100x faster than software solutions running on low-power microcontrollers.

By integrating a dedicated neural network accelerator with a pair of microcontroller cores, the device enables 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 therefore be made more efficient.

At the heart of the product is specialised hardware designed to minimise the energy consumption and latency of convolutional neural networks (CNN). This hardware runs with minimal intervention from any microcontroller core, streamlining operation. 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, users can use one of the two integrated microcontroller cores: the ultralow-power Arm Cortex-M4 core or the even lower-power RISC-V core.