TinyML: The challenges and opportunities of low-power ML applications

#News(IoTStack) [ via IoTGroup ]

Headings…
TinyML: The challenges and opportunities of low-power ML applications

Learn faster. Dig deeper. See farther.

Auto extracted Text……

Pete Warden has spent the last few years laser focused on building a useful TinyML platform, a scheme to combine battery-powered, small, low-powered CPUs and controllers with machine learning algorithms.
Many of the tasks in the billions of microcontrollers and CPUs included in small, battery-powered devices can be improved or made more useful with machine learning.
Pete Warden has an ambitious goal: he wants to build machine learning (ML) applications that can run on a microcontroller for a year using only a hearing aid battery for power.
If a low-power device needs to communicate with the outside world, it can’t be “chatty”; it needs to turn off the radio, turning it on only to transmit short bursts of data.
Turning off the radio inverts our models for machine learning on small devices.
That’s just too power-hungry for TinyML; we can’t do machine learning by sending data to big iron in the cloud.
TensorFlow Lite can be used to run models on Android and iOS phones; though, like the Raspberry Pi, it’s hard to consider a modern smartphone a “small” processor.
TinyML can be used anywhere it’s difficult to supply power.
Ideally, you would like intelligent sensors that can send wireless notifications only when needed; they might be powered by a battery, or even by generating electricity from vibration.
Many of his devices couldn’t tolerate the noise created by a traditional power supply and had to be battery powered.
All of these applications require machine learning and sensors in places where it’s inconvenient or impossible to supply commercial power.
While these constraints differ from TinyML, they have the same solution: processors have to be slow, reliable, with limited memory, and as small a footprint as possible.
While the constraints are different, the solution is the same; and as these processors incorporate machine learning, the answer will be (and already is) TinyML

Read More..
AutoTextExtraction by Working BoT using SmartNews 1.0299999999 Build 26 Aug 2019