As a partner in TinyML, Aizip works with ADI to provide intelligent solutions to customers.
ADI’s MAX78000 neural-network microcontroller detects people within an image using Aizip’s Visual Wake Words (VWW) model at just 0.7 milljoules (mJ) per inference. This is 100 times lower than conventional software solutions, and the most economical and efficient loT person-detection solution available. The low-power network provides longer operation for battery-powered loT systems that require human-presence detection, including building energy-management and smart security cameras.
“The combination of ADI’s ultra-low power chip solutions and Aizip’s compact AI models is an important development that will enable many novel and exciting applications in the loT world,” said Professor Bruno Olshausen at UC Berkeley, a highly recognized expert in neural computation/neural network models who also serves as an advisor to Aizip.
Extended Battery Life: Efficient AI model and low power microcontroller system-on-chip (SoC) reduce inference energy to 0.7 mJ, allowing 13 million inferences from a single AA/LR6 battery.
Cost-Effective Intelligence at the Edge: Extreme model compression enables accurate smart vision with a memory- constrained, low-cost AI accelerated microcontroller and budget-friendly image sensors.
Target Markets and Applications