TinyML is Breathing Life into Billions of Devices
upstart writes in with an IRC submission:
[Ed note: Sometimes stories come in where it is hard to tell whether they should be accepted and put before the community. This story is one of those. It certainly seems interesting, but I quite frankly can't tell whether this is the very start of something big, or a bunch of marketing hype. If it is as capable as claimed, I would expect reference implementations should be readily available for a PC - where are they? So, feel free to tear this to shreds or sing its praises in the comments. --martyb]
TinyML is breathing life into billions of devices:
Until now building machine learning (ML) algorithms for hardware meant complex mathematical modes based on sample data, known as "training data," in order to make predictions or decisions without being explicitly programmed to do so. And if this sounds complex and expensive to build, it is. On top of that, traditionally ML related tasks were translated to the cloud, creating latency, consuming scarce power, and putting machines at the mercy of connection speeds. Combined, these constraints made computing at the Edge slower, more expensive, and less predictable. Tiny Machine Learning (TinyML) is the latest embedded software technology that moves hardware into an almost magical realm, where machines can automatically learn and grow through use, like a primitive human brain.
But thanks to recent advances companies are turning to TinyML as the latest trend in building product intelligence. Arduino, the company best known for open-source hardware is making TinyML available for millions of developers, and now together with Edge Impulse, they are turning the ubiquitous Arduino board into a powerful embedded ML platform, like the Arduino Nano 33 BLE Sense and other 32-bit boards. With this partnership you can run powerful learning models based on artificial neural networks (ANN) reaching and sampling tiny sensors along with low powered microcontrollers. Over the past year great strides were made in making deep learning models smaller, faster, and runnable on embedded hardware through projects like TensorFlow Lite for Microcontrollers, uTensor, and Arm's CMSIS-NN; but building a quality dataset, extracting the right features, training and deploying these models is still complicated. TinyML was the missing link between Edge hardware and device intelligence, now coming to fruition.
The story continues with claims of places where this has apparently been successfully applied. There is a tinyML Foundation web site which continues with prognostications of tremendous growth just ahead.
Read more of this story at SoylentNews.