Train All The Things Contest Update

Back in January when we announced the Train All the Things contest, we weren’t sure what kind of entries we’d see. Machine learning is a huge and rapidly evolving field, after all, and the traditional barriers that computationally intensive processes face have been falling just as rapidly. Constraints are fading away, and we want you to explore this wild new world and show us what you come up with.

Where Do You Run Your Algorithms?

To give your effort a little structure, we’ve come up with four broad categories:

  • Machine Learning on the Edge
    • Edge computing, where systems reach out to cloud resources but run locally, is all the rage. It allows you to leverage the power of other people’s computers the cloud for training a model, which is then executed locally. Edge computing is a great way to keep your data local.
  • Machine Learning on the Gateway
    • Pi’s, old routers, what-have-yous – we’ve all got a bunch of devices laying around that bridge space between your local world and the cloud. What can you come up with that takes advantage of this unique computing environment?
  • Machine Learning in the Cloud
    • Forget about subtle — this category unleashes the power of the cloud for your application. Whether it’s Google, Azure, or AWS, show us what you can do with all that raw horsepower at your disposal.
  • Artificial Intelligence Blinky
    • Everyone’s “hardware ‘Hello, world'” is blinking an LED, and this is the machine learning version of that. We want you to use a simple microprocessor to run a machine learning algorithm. Amaze us with what you can make an Arduino do.

These Hackers Trained Their Projects, You Should Too!

We’re a little more than a month into the contest. We’ve seen some interesting entries bit of course we’re hungry for more! Here are a few that have caught our eye so far:

  • Intelligent Bat Detector – [Tegwyn☠Twmffat] has bats in his… backyard, so he built this Jetson Nano-powered device to capture their calls and classify them by species. It’s a fascinating adventure at the intersection of biology and machine learning.
  • Blackjack Robot – RAIN MAN 2.0 is [Evan Juras]’ cure for the casino adage of “The house always wins.” We wouldn’t try taking the Raspberry Pi card counter to Vegas, but it’s a great example of what YOLO can do.
  • AI-enabled Glasses – AI meets AR in ShAIdes, [Nick Bild]’s sunglasses equipped with a camera and Nano to provide a user interface to the world. Wave your hand over a lamp and it turns off. Brilliant!

You’ve got till noon Pacific time on April 7, 2020 to get your entry in, and four winners from each of the four categories will be awarded a $100 Tindie gift card, courtesy of our sponsor Digi-Key. It’s time to ramp up your machine learning efforts and get a project entered! We’d love to see more examples of straight cloud AI applications, and the AI blinky category remains wide open at this point. Get in there and give machine learning a try!

Assistive Specs Help Jog Your Memory

It’s something that can happen to all of us, that we forget things. Young and old, we know things are on our to-do list but in the heat of the moment they disappear from our minds and we miss them. There are a myriad of technological answers to this in the form of reminders and calendars, but [Nick Bild] has come up with possibly the most inventive yet. His Newrons project is a pair of glasses with a machine vision camera, that flashes a light when it detects an object in its field of view associated with a calendar entry.

At its heart is a JeVois A33 Smart Machine Vision Camera, which runs a neural network trained on an image dataset. It passes its sightings to an Arduino Nano IoT fitted with a real-time clock, that pulls appointment information from Google Calendar and flashes the LED when it detects a match between object and event. His example which we’ve placed below the break is a pill bottle triggering a reminder to take the pills.

We like this idea, but can’t help thinking that it has a flaw in that the reminder relies on the object moving into view. A version that tied this in with more conventional reminding based upon the calendar would address this, and perhaps save the forgetful a few problems.

Continue reading “Assistive Specs Help Jog Your Memory”

Sound-Triggered Eye Protection For The Forgetful Among US

Eyes are fragile things. They tend to fail under extreme heat, pressure, and are easily damaged by flying objects. Enterprising humans have developed a wide range of eye protection solutions, but most only work when the user remembers to put them on. [gocivici] had just such a problem, forgetting to put his safety glasses back on when working. Naturally, the solution was found through hacking.

The build starts with a regular baseball cap. [gocivici] fitted an Arduino nano, which is connected to a small microphone. The Arduino uses the microphone to determine the sound level in the room. Above a certain trigger level, the Arduino triggers a servo to move protective glasses into place in front of the wearer’s eyes, protecting them from flying shrapnel from whatever they may be working on.

It’s a fun build, that obviously still has the pitfall that you’re going to get hurt if you forget to wear your magic hat for the day. Another approach could be putting your multimeter display in your goggles so you never want to take them off in the first place. Video after the break.

Continue reading “Sound-Triggered Eye Protection For The Forgetful Among US”

Overlooked Minimalism In Assistive Technology

If your eyes are 20/20, you probably do not spend much time thinking about prescription eyeglasses. It is easy to overlook that sort of thing, and we will not blame you. When we found this creation, it was over two years old, but we had not seen anything quite like it. The essence of the Bear Paw Assistive Eating Aid is a swiveling magnet atop a suction cup base. Simple right? You may already be thinking about how you could build or model that up in a weekend, and it would not be a big deal. The question is, could you make something like this if you had not seen it first?

Over-engineered inventions with lots of flexibility and room for expansion have their allure. When you first learn Arduino, every problem looks like a solution for that inexpensive demo board and one day you find yourself wearing an ATMEGA wristwatch. Honestly, we love those just as much but for an entirely different reason. When all the bells and whistles are gone, when there is nothing left but a robust creation that, “just works,” you have created something beautiful. Judging by the YouTube comments of the video, which can be seen below the break, those folks have no trouble overlooking the charm of this device since the word “beard” appears 95 times and one misspelling for a “bread” count of one. Hackaday readers are a higher caliber and should be able to appreciate its elegance.

The current high-tech solution for self-feeding is a robot arm, not unlike this one which is where our minds went when we heard about an invention about eating without using hands, and we will always be happy to talk about robot arms.

Continue reading “Overlooked Minimalism In Assistive Technology”

Twenty Projects That Just Won The Human Computer Interface Challenge

The greatest hardware competition on the planet is going on right now. The Hackaday Prize is the Oscars of Open Hardware. It’s the Nobel Prize of building a thing. It’s the Fields Medal of firmware development, and simply making it to the finals grants you a knighthood in the upper echelon of hardware developers.

Last week, we wrapped up the fourth challenge in The Hackaday Prize, the Human Computer Interface challenge. Now we’re happy to announce twenty of those projects have been selected to move onto the final round and have been awarded a $1000 cash prize. Congratulations to the winners of the Human Computer Interface Challenge in this year’s Hackaday Prize. Here are the winners, in no particular order:

Human Computer Interface Challenge Hackaday Prize Finalists:

Continue reading “Twenty Projects That Just Won The Human Computer Interface Challenge”

The Precise Science Of Whacking A Wine Glass

It’s common knowledge that tapping a wine glass produces a pitch which can be altered by adjusting the level of the tipple of choice inside. By filling twelve glasses with different amounts of liquid and tuning them to the twelve notes of the scale, it’s possible to make a one-octave instrument – though the speed and polyphony are bottle-necked by the human operator. If you think it sounds like a ripe project for automation, you’re correct: [Bitluni’s lab] has done what needed to be done, and created a MIDI instrument which plays the glasses using mallets.

Electronically it’s a simple build – some 12 V solenoids driven by MOSFETs, with an Arduino in charge. For the mechanical build, a 3D printer proved very useful, as each mallet could be made identical, ensuring a consistent tone across all glasses. Rubber covers printed in flexible filament were fitted to reduce the overtones and produce a clearer sound. [Bitluni] also utilised different types of glasses for the low and high pitches, which also helped to improve the clarity of the tone.

MIDI is of course the perfect protocol for this application; simple, lightweight and incredibly widely used, it’s the hacker’s delight for projects like this. The instrument can perform pre-programmed sequences, or be played live with a MIDI controller. Both of these are shown in the video after the break – stick around for a unique rendition of Flight Of The Bumblebee. For a more compact wine glass based music creation solution, we recommend this nifty project, which alters pitch using a water balloon raised and lowered into the glass by a servo.  Continue reading “The Precise Science Of Whacking A Wine Glass”

This Radio Gets Pour Reception

When was the last time you poured water onto your radio to turn it on?

Designed collaboratively by [Tore Knudsen], [Simone Okholm Hansen] and [Victor Permild], Pour Reception seeks to challenge what constitutes an interface, and how elements of play can create a new experience for a relatively everyday object.

Lacking buttons or knobs of any kind, Pour Reception appears an inert acrylic box with two glasses resting on top. A detachable instruction card cues the need for water, and pouring some into the glasses wakes the radio.

Continue reading “This Radio Gets Pour Reception”