machine learning

243 Articles

Self-Driving Laboratories Do Research On Autopilot

September 29, 2022 by 16 Comments

Scientific research is a messy business. The road to learning new things and making discoveries is paved with hard labor, tough thinking, and plenty of dead ends. It’s a time-consuming, expensive endeavor, and for every success, there are thousands upon thousands of failures.

It’s a process so inefficient, you would think someone would have automated it already. The concept of the self-driving laboratory aims to do exactly that, and could revolutionize materials research in particular.

Continue reading “Self-Driving Laboratories Do Research On Autopilot” →

Tesla’s Dojo Is An Interesting CPU Design

September 6, 2022 by 29 Comments

What do you get when you cross a modern super-scalar out-of-order CPU core with more traditional microcontroller aspects such as no virtual memory, no memory cache, and no DDR or PCIe controllers? You get the Tesla Dojo, which Chips and Cheese recently did a deep dive on.

It starts with a comparison to the IBM Cell processors. The Cell of the mid-2000s featured something called the SPE (Synergistic Processing Elements). They were smaller cores focused on vector processing or other specialized types of workloads. They didn’t access the main memory and had to be given tasks by the fully featured CPU. Dojo has 1.25MB of SRAM that it can use as working memory with five ports, but it has no cache or virtual memory. It uses DMA to get the information it needs via a mesh system. The front end pulls RISC-V-like (heavily MIPS-inspired) instructions into a small instruction cache and decodes eight instructions per cycle. Continue reading “Tesla’s Dojo Is An Interesting CPU Design” →

Truthsayer Uses Facial Recognition To See If You’re Telling The Truth

September 2, 2022 by 18 Comments

It’s hard to watch [Mark Zuckerberg]’s 2018 Congressional testimony and not come to the conclusion that he is, at a minimum, quite a bit different than the average person. Of course, having built a multibillion-dollar company that drastically changed everything about the way people communicate is pretty solid evidence of that, but the footage at least made a fun test case for this AI truth-detecting algorithm.

Now, we’re not saying that anyone in these videos was lying, and neither is [Fletcher Heisler]. His algorithm, which analyzes video of a person and uses machine vision to pick up cues that might be associated with the stress of untruthfulness, is far from perfect. But as the first video below shows, it is a lot of fun to see it at work. The idea is to capture data like pulse rate, gaze direction, blink rate, mouth posture, and even hand position and use them as a proxy for lying. The second video, from [Fletcher]’s recent DEFCON talk, has much more detail.

The key to all this is finding human faces in a video — a task that seemed to fail suspiciously frequently when [Zuck] was on camera — using OpenCV and MediaPipe’s Face Mesh. The subject’s pulse is detected by watching for subtle changes in the color of a subject’s cheeks as blood flows through them, which we’ve heard about plenty of times but never before seen presented so clearly and executed so simply. Gaze direction, blinking, and lip compression are fairly easy to detect too. [Fletcher] also threw in the FER library for facial expression recognition, to get an idea of the subject’s mood. Together, these cues form a rough estimate of the subject’s truthiness, which [Fletcher] is quick to point out is just for entertainment purposes and totally shouldn’t be used on your colleagues on the next Zoom call.

Does [Fletcher]’s facial mesh look familiar? It should, since we once watched him twitch his way through a coding interview.

Continue reading “Truthsayer Uses Facial Recognition To See If You’re Telling The Truth” →

Blog Title Optimizer Uses AI, But How Well Does It Work?

August 21, 2022 by 11 Comments

[Max Woolf] sometimes struggles to create ideal headlines for his blog posts, and decided to apply his experience with machine learning to the problem. He asked: could an AI be trained to optimize his blog titles? It is a fascinating application of natural language processing, and [Max] explains all about what it does and how it works.

The machine learning framework [Max] uses is GPT-3, a language model that works with natural-seeming human language that is capable of being tweaked in different ways. [Max] uses OpenAI’s GPT-3 API (which, by the way, is much easier to experiment with than one might think) and here is the basic workflow for his title optimizer:

  1. The optimizer takes as input a blog post title to optimize.
  2. OpenAI’s pre-trained GPT-3 engine is used to generate six alternate titles.
  3. For each of those alternate titles, a fine-tuned version of GPT-3 is consulted to judge how “good” they are based on custom training data. (“Good” in this context means “similar to titles of successful submissions on Hacker News“, but more on that in a moment.)
  4. Print the results.

Continue reading “Blog Title Optimizer Uses AI, But How Well Does It Work?” →

Machine Learning Baby Monitor Prevents The Hunger Games

July 23, 2022 by 25 Comments

Newborn babies can be tricky to figure out, especially for first-time parents. Despite the abundance of unsolicited advice proffered by anyone who ever had a baby before — and many who haven’t — most new parents quickly get in sync with the baby’s often ambiguous signals. But [Caleb] took his observations of his newborn a step further and built a machine-learning hungry baby early warning system that’s pretty slick.

Normally, babies are pretty unsubtle about being hungry, and loudly announce their needs to the world. But it turns out that crying is a lagging indicator of hunger, and that there are a host of face, head, and hand cues that precede the wailing. [Caleb] based his system on Google’s MediaPipe library, using his baby monitor’s camera to track such behaviors as lip smacking, pacifier rejection, fist mouthing, and rooting, all signs that someone’s tummy needs filling. By putting together a system to recognize these cues and assign a weight to them, [Caleb] now gets a text before the baby gets to the screaming phase, to the benefit of not only the little nipper but to his sleep-deprived servants as well. The video below has some priceless bits in it; don’t miss [Baby Caleb] at 5:11 or the hilarious automatic feeder gag at the end.

We’ve seen some interesting videos from [Caleb] recently, mostly having to do with his dog’s bathroom habits and getting help cleaning up afterward. We can only guess how those projects will be leveraged when this kid gets a little older and starts potty training.

Continue reading “Machine Learning Baby Monitor Prevents The Hunger Games” →

Insect class-order-family-genus-species chart with drawn examples

Neural Network Identifies Insects, Outperforming Humans

July 16, 2022 by 15 Comments

There are about one million known species of insects – more than for any other group of living organisms. If you need to determine which species an insect belongs to, things get complicated quick. In fact, for distinguishing between certain kinds of species, you might need a well-trained expert in that species, and experts’ time is often better spent on something else. This is where CNNs (convolutional neural networks) come in nowadays, and this paper describes a CNN doing just as well if not better than human experts.

Continue reading “Neural Network Identifies Insects, Outperforming Humans” →

Computer Vision Extracts Lightning From Footage

July 1, 2022 by 16 Comments

Lightning is one of the more mysterious and fascinating phenomenon on the planet. Extremely powerful, but each strike on average only has enough energy to power an incandescent bulb for an hour. The exact mechanism that starts a lightning strike is still not well understood. Yet it happens 45 times per second somewhere on the planet. While we may not gain a deeper scientific appreciation of lightning anytime soon, but we can capture it in various photography thanks to this project which leverages computer vision machine learning to pull out the best frames of lightning.

The project’s creator, [Liam], built this as a tool for stormchasers and photographers so that they can film large amounts of time and not have to go back through their footage manually to pull out the frames with lightning strikes. The project borrows from a similar project, but this one adds Python 3 capabilities and runs on a tiny netbook for more easy field deployment. It uses OpenCV for object recognition, using video files as the source data, and features different modes to recognize different types of lightning.

The software is free and open source, and releases are supported for both Windows and Linux. So far, [Liam] has been able to capture all kinds of electrical atmospheric phenomenon with it including lightning, red sprites, and elves. We don’t see too many projects involving lightning around here, partly because humans can only generate a fraction of the voltage potential needed for the average lightning strike.