Machine learning is starting to come online in all kinds of arenas lately, and the trend is likely to continue for the forseeable future. What was once only available for operators of supercomputers has found use among anyone with a reasonably powerful desktop computer. The downsizing isn’t stopping there, though, as Microsoft is pushing development of machine learning for embedded systems now.

The Embedded Learning Library (ELL) is a set of tools for allowing Arduinos, Raspberry Pis, and the like to take advantage of machine learning algorithms despite their small size and reduced capability. Microsoft intended this library to be useful for anyone, and has examples available for things like computer vision, audio keyword recognition, and a small handful of other implementations. The library should be expandable to any application where machine learning would be beneficial for a small embedded system, though, so it’s not limited to these example applications.

There is one small speed bump to running a machine learning algorithm on your Raspberry Pi, though. The high processor load tends to cause small SoCs to overheat. But adding a heatsink and fan is something we’ve certainly seen before. Don’t let your lack of a supercomputer keep you from exploring machine learning if you see a benefit to it, and if you need more power than just one Raspberry Pi you can always build a cluster to get your task done just a little bit faster, too.

Thanks to [Baldpower] for the tip!

If you haven’t jumped on the ESP8266 bandwagon yet, it might be a good time to get started. If you can program an Arduino you have pretty much all of the skills you’ll need to get an ESP8266 up and running. And, if you need a good idea for a project to build with one of these WiFi miracle chips, look no further than [Ben Buxton]’s dated, but awesome, NTP clock.

While the ESP8266 started out as an inexpensive, reliable way to get WiFi capability on essentially anything (and paving the way for a plethora of Internet of Things projects), it was quickly hacked to become a fully programmable development board that can stand on its own. To that end, [Ben] has recognized its capability to run a very minimalistic NTP clock. The standard C++/Arduino environment is available, so he didn’t have to learn any new skills. The parts list is stripped down as well: besides the ESP8266, there’s little more than the four-part seven-segment display. There’s even an Arudino library for these chips that [Ben] made great use of. From there, it’s just a matter of wiring it all up and syncing it with an NTP server.

While it’s not the most involved hack ever, it’s good to be reminded that these chips are cheap and readily available for literally anything that you could imagine. If you haven’t started yet, there’s no reason not to. You can use them to control something like an irrigation system, or if you’re even more adventurous, they can run a 3D printer, too.

Thanks [Itay] for the tip!