Remoticon Video: How To Use Machine Learning With Microcontrollers

December 4, 2020 by Mike Szczys 5 Comments

Going from a microcontroller blinking an LED, to one that blinks the LED using voice commands based on a data set that you trained on a neural net work is a “now draw the rest of the owl” problem. Lucky for us, Shawn Hymel walks us through the entire process during his Tiny ML workshop from the 2020 Hackaday Remoticon. The video has just now been published and can be viewed below.

This is truly an end-to-end Hello World for getting machine learning up and running on a microcontroller. Shawn covers the process of collecting and preparing the audio samples, training the data set, and getting it all onto the microcontroller. At the end of two hours, he’s able to show the STM32 recognizing and responding to two different spoken words. Along the way he pauses to discuss the context of what’s happening in every step, which will help you go back and expand in those areas later to suit your own project needs.

Continue reading “Remoticon Video: How To Use Machine Learning With Microcontrollers” →

Robots Can Finally Answer, Are You Talking To Me?

November 8, 2020 by Matthew Carlson 25 Comments

Voice Assistants, love them, or hate them, are becoming more and more commonplace. One problem for voice assistants is the situation of multiple devices listening in the same place. When a command is given, which device should answer? Researchers at CMU’s Future Interfaces Group [Karan Ahuja], [Andy Kong], [Mayank Goel], and [Chris Harrison] have an answer; smart assistants should try to infer if the user is facing the device they want to talk to. They call it direction-of-voice or DoV.

Currently, smart assistants use a simple race to see who heard it first. The reasoning is that the device you are closest to will likely hear it first. However, in situations with echos or when you’re equidistant from multiple devices, the outcome can seem arbitrary to a user.

The implementation of DoV uses an Extra-Trees Classifier from the python sklearn toolkit. Several other machine learning algorithms were considered, but ultimately efficiency won out and Extra-Trees was selected. Another interesting facet of the research was determining what facing really means. The team had humans ‘listeners’ stand in for smart assistants. A ‘talker’ would speak the key phrase while the ‘listener’ determined if the talker was facing them or not. Based on their definition of facing, the system can determine if someone is facing the device with 90% accuracy that rises to 93% with per-room calibration.

Their algorithm as well as the data they collected has been open-sourced on GitHub. Perhaps when you’re building your own voice assistant, you can incorporate DoV to improve wake-word accuracy.

Continue reading “Robots Can Finally Answer, Are You Talking To Me?” →

Training A Neural Network To Play A Driving Game

November 7, 2020 by Lewin Day 12 Comments

Often, when we think of getting a computer to complete a task, we contemplate creating complex algorithms that take in the relevant inputs and produce the desired behaviour. For some tasks, like navigating a car down a road, the sheer multitude of input data and its relationship to the desired output is so complex that it becomes near-impossible to code a solution. In these cases, it can make more sense to create a neural network and train the computer to do the job, as one would a human. On a more basic level, [Gigante] did just that, teaching a neural network to play a basic driving game with a genetic algorithm.

The game consists of a basic top-down 2D driving game. The AI is given the distance to the edge of the track along five lines at different angles projected from the front of the vehicle. The AI also knows its speed and direction. Given these 7 numbers, it calculates the outputs for steering, braking and acceleration to drive the car.

To train the AI, [Gigante] started with 650 AIs, and picked the best performer, which just barely managed to navigate the first two corners. Marking this AI as the parent of the next generation, the AIs were iterated with random mutations. Each generation showed some improvement, with [Gigante] picking the best performers each time to parent the next generation. Within just four iterations, some of the cars are able to complete a full lap. With enough training, the cars are able to complete the course at great speed without hitting the walls at all.

It’s a great example of machine learning and the use of genetic algorithms to improve fitness over time. [Gigante] points out that there’s no need for a human in the loop either, if the software is coded to self-measure the fitness of each generation. We’ve seen similar techniques used to play Mario, too. Video after the break.

Continue reading “Training A Neural Network To Play A Driving Game” →

Jetson Emulator Gives Students A Free AI Lesson

October 26, 2020 by Tom Nardi 4 Comments

With the Jetson Nano, NVIDIA has done a fantastic job of bringing GPU-accelerated machine learning to the masses. For less than the cost of a used graphics card, you get a turn-key Linux computer that’s ready and able to handle whatever AI code you throw at it. But if you’re trying to set up a lab for 30 students, the cost of even relatively affordable development boards can really add up.

Which is why [Tea Vui Huang] has developed jetson-emulator. This Python library provides a work-alike environment to NVIDIA’s own “Hello AI World” tutorials designed for the Jetson family of devices, with one big difference: you don’t need the actual hardware. In fact, it doesn’t matter what kind of computer you’ve got; with this library, anything that can run Python 3.7.9 or better can take you through NVIDIA’s getting started tutorial.

So what’s the trick? Well, if you haven’t guessed already, it’s all fake. Obviously it can’t actually run GPU-accelerated code without a GPU, so the library [Tea] has developed simply pretends. It provides virtual images and even “live” camera feeds to which randomly generated objects have been assigned.

The original NVIDIA functions have been rewritten to work with these feeds, so when you call something like net.Classify(img) against one of them you’ll get a report of what faux objects were detected. The output will look just like it would if you were running on a real Jetson, down to providing fictitious dimensions and positions for the bounding boxes.

If you’re a hacker looking to dive into machine learning and computer vision, you’d be better off getting a $59 Jetson Nano and a webcam. But if you’re putting together a workshop that shows a dozen people the basics of NVIDIA’s AI workflow, jetson-emulator will allow everyone in attendance to run code and get results back regardless of what they’ve got under the hood.

Exploring Animal Intelligence Hack Chat

October 19, 2020 by Dan Maloney 4 Comments

Join us on Wednesday, October 21st at noon Pacific for the Exploring Animal Intelligence Hack Chat with Hans Forsberg!

From our lofty perch atop the food chain it’s easy to make the assumption that we humans are the last word in intelligence. A quick glance at social media or a chat with a random stranger at the store should be enough to convince you that human intelligence isn’t all it’s cracked up to be, or at least that it’s not evenly distributed. But regardless, we are pretty smart, thanks to those big, powerful brains stuffed into our skulls.

We’re far from the only smart species on the planet, though. Fellow primates and other mammals clearly have intelligence, and we’ve seen amazingly complex behaviors from animals in just about every taxonomic rank. But it’s the birds who probably stuff the most functionality into their limited neural hardware, with tool use, including the ability to make new tools, being common, along with long-distance navigation, superb binocular vision, and of course the ability to rapidly maneuver in three-dimensions while flying.

Hans Forsberg has taken an interest in avian intelligence lately, and to explore just what’s possible he devised a fiendishly clever system to train his local magpie flock to clean up his yard, which he calls “BirdBox”. We recently wrote up his initial training attempts, which honestly bear a strong resemblance to training a machine learning algorithm, which is probably no small coincidence since his professional background is with neural networks. He has several years of work into his birds, and he’ll stop by the Hack Chat to talk about what goes into leveraging animal intelligence, what we can learn about our systems from it, and where BirdBox goes next.

Our Hack Chats are live community events in the Hackaday.io Hack Chat group messaging. This week we’ll be sitting down on Wednesday, October 21 at 12:00 PM Pacific time. If time zones baffle you as much as us, we have a handy time zone converter.

Click that speech bubble to the right, and you’ll be taken directly to the Hack Chat group on Hackaday.io. You don’t have to wait until Wednesday; join whenever you want and you can see what the community is talking about.

Continue reading “Exploring Animal Intelligence Hack Chat” →

Tube Amp Is Modeled With The Power Of AI

October 11, 2020 by Matthew Carlson 4 Comments

There is a certain magic and uniqueness to hardware, particularly when it comes to audio. Tube amplifiers are well-known and well-loved by audio enthusiasts and musicians alike. However, that uniqueness also comes with the price of the fact that gear takes up space and cannot be configured outside the bounds of what it was designed to do. [keyth72] has decided to take it upon themselves to recreate the smooth sound of the Fenders Blues Jr. small tube guitar amp. But rather than using hardware or standard audio software, the magic of AI was thrown at it.

In some ways, recreating a transformation is exactly what AI is designed for. There’s a clear and recordable input with a similar output. In this case, [keyth72] recorded several guitar sessions with the guitar audio sent through the device they wanted to recreate. Using WaveNet, they created a model that applies the transform to input audio in real-time. The Gain and EQ knobs were handled outside the model itself to keep things simple. Instructions on how to train your own model are included on the GitHub page.

While the model is simply approximating the real hardware, it still sounds quite impressive, and perhaps the next time you need a particular sound of your home-built amp or guitar pedal, you might reach for your computer instead.
Continue reading “Tube Amp Is Modeled With The Power Of AI” →

NVIDIA Announces $59 Jetson Nano 2GB, A Single Board Computer With Makers In Mind

October 5, 2020 by Tom Nardi 47 Comments

NVIDIA kicked off their line of GPU-accelerated single board computers back in 2014 with the Jetson TK1, a $200 USD development system for those looking to get involved with the burgeoning world of so-called “edge computing”. It was designed to put high performance computing in a small and energy efficient enough package that it could be integrated directly into products, rather than connecting to a data center half-way across the world.

The TK1 was an impressive piece of hardware, but not something the hacker and maker community was necessarily interested in. For one thing, it was fairly expensive. But perhaps more importantly, it was clearly geared more towards industry types than consumers. We did see the occasional project using the TK1 and the subsequent TX1 and TX2 boards, but they were few and far between.

Then came the Jetson Nano. Its 128 core Maxwell CPU still packed plenty of power and was fully compatible with NVIDIA’s CUDA architecture, but its smaller size and $99 price tag made it far more attractive for hobbyists. According to the company’s own figures, the number of active Jetson developers has more than tripled since the Nano’s introduction in March of 2019. With the platform accessible to a larger and more diverse group of users, new and innovative applications for machine learning started pouring in.

Cutting the price of the entry level Jetson hardware in half was clearly a step in the right direction, but NVIDIA wanted to bring even more developers into the fray. So why not see if lightning can strike twice? Today they’ve officially announced that the new Jetson Nano 2GB will go on sale later this month for just $59. Let’s take a close look at this new iteration of the Nano to see what’s changed (and what hasn’t) from last year’s model.

Continue reading “NVIDIA Announces $59 Jetson Nano 2GB, A Single Board Computer With Makers In Mind” →