With nearly sixty exciting entries, the Train All the Things contest, presented in partnership with Digi-Key, has drawn to a close and today we are happy to share news of the winning projects. The challenge at hand was to show off a project using some type of Machine Learning and there were plenty of takes on this theme displayed.
Perhaps the most impressive project is the Intelligent Bat Detector by [Tegwyn☠Twmffat] which claims the “ML on the Edge” award. His project, seen above, seeks not only to detect the presence of bats through the sounds they make during echolocation, but to identify the type of bat as well. Having been through a number of iterations, the bat detector, based on Nvidia Jetson Nano and a Raspberry Pi, can classify several types of bats, and a set of house keys (for a “control”). It’s also been impeccably documented and serves as a great example of how to get into machine learning.
The Soldering LIghtsaber takes the “ML Blinky” award for using machine learning in the microcontroller realm. This clever use of the concept seeks one thing: destroying the wait times for your soldering iron to heat up. It takes time to make temperature readings while the iron heats up, if you can do away with this step it speeds things up greatly. By sampling results of different voltages and heating times, machine learning establishes its own guidelines for how to pour electricity into the heating element without checking for feedback, and coming out the other side at the perfect temperature.
AI Powered Bulls*** Detector
Wearables Fitness Trackers for Mental Health
Rounding up our final two winners, the AI Powered Bull**** Detector claims the “ML on the Gateway” award, and
Hacking Wearables for Mental Health and More which won in the “ML on the Cloud” category.
The idea behind our illuminated poop emoji project is to detect human speech and make a judgement on whether the comment is valid, or BS. It does this by leveraging a learning set of comments that have previously been identified as BS and making an association with the currently uttered words.
Wearables for mental health is a wonderful project that was previously recognized in the 2018 Hackaday Prize. Economies of scale have made these wearables quite affordable as a way to add a sensor suite to behavior analysis. But of course you need a way to process all of the sensor data, a perfect task for a cloud-based machine learning application.
All four winners received a $100 gift code to Tindie. Don’t forget to check out all of the other interesting projects that were entered in this contest!
The old way was to write clever code that could handle every possible outcome. But what if you don’t know exactly what your inputs will look like, or just need a faster route to the final results? The answer is Machine Learning, and we want you to give it a try during the Train All the Things contest!
It’s hard to find a more buzz-worthy term than Artificial Intelligence. Right now, where the rubber hits the road in AI is Machine Learning and it’s never been so easy to get your feet wet in this realm.
From an 8-bit microcontroller to common single-board computers, you can do cool things like object recognition or color classification quite easily. Grab a beefier processor, dedicated ASIC, or lean heavily into the power of the cloud and you can do much more, like facial identification and gesture recognition. But the sky’s the limit. A big part of this contest is that we want everyone to get inspired by what you manage to pull off.
Yes, We Do Want to See Your ML “Hello World” Too!
Wait, wait, come back here. Have we already scared you off? Don’t read AI or ML and assume it’s not for you. We’ve included a category for “Artificial Intelligence Blinky” — your first attempt at doing something cool.
Need something simple to get you excited? How about Machine Learning on an ATtiny85 to sort Skittles candy by color? That uses just one color sensor for a quick and easy way to harvest data that forms a training set. But you could also climb up the ladder just a bit and make yourself a camera-based LEGO sorter or using an IMU in a magic wand to detect which spell you’re casting. Need more scientific inspiration? We’re hoping someday someone will build a training set that classifies microscope shots of micrometeorites. But we’d be equally excited with projects that tackle robot locomotion, natural language, and all the other wild ideas you can come up with.
Our guess is you don’t really need prizes to get excited about this one… most people have been itching for a reason to try out machine learning for quite some time. But we do have $100 Tindie gift certificates for the most interesting entry in each of the four contest categories: ML on the edge, ML on the gateway, AI blinky, and ML in the cloud.
Get started on your entry. The Train All The Things contest is sponsored by Digi-Key and runs until April 7th.