AML100 General Description

The AML100 extends battery life by up to 20x over traditional digital always-on systems. As the first product in Aspinity’s analog machine learning (analogML?) core family, the AML100 is the only machine learning chip to intelligently reduce the amount of data that moves through the always-on system while the data are still analog. It keeps the higher-power digital components asleep unless important data are detected. By performing machine learning in analog, the AML100 eliminates the digitization, digital processing, and transmission of irrelevant noise, reducing always-on system power by >95 to unlock the potential of thousands of new applications running on battery.

Features

?

World’s first fully analog machine learning chip

?

Processes natively analog data

?

Uses near-zero power to inference and to detect events

?

Consumes <20μA when always-sensing

?

Intelligently reduces analog data by 100x

?

Supports up to 4 analog sensors

?

Easy to integrate into current digital architectures

?

7mm x 7mm 48-pin QFN package