AI On Raspberry Pi With The Intel Neural Compute Stick

January 31, 2019 by Sean Boyce 58 Comments

I’ve always been fascinated by AI and machine learning. Google TensorFlow offers tutorials and has been on my ‘to-learn’ list since it was first released, although I always seem to neglect it in favor of the shiniest new embedded platform.

Last July, I took note when Intel released the Neural Compute Stick. It looked like an oversized USB stick, and acted as an accelerator for local AI applications, especially machine vision. I thought it was a pretty neat idea: it allowed me to test out AI applications on embedded systems at a power cost of about 1W. It requires pre-trained models, but there are enough of them available now to do some interesting things.

You can add a few of them in a hub for parallel tasks. Image credit Intel Corporation.

I wasn’t convinced I would get great performance out of it, and forgot about it until last November when they released an improved version. Unambiguously named the ‘Neural Compute Stick 2’ (NCS2), it was reasonably priced and promised a 6-8x performance increase over the last model, so I decided to give it a try to see how well it worked.

I took a few days off work around Christmas to set up Intel’s OpenVino Toolkit on my laptop. The installation script provided by Intel wasn’t particularly user-friendly, but it worked well enough and included several example applications I could use to test performance. I found that face detection was possible with my webcam in near real-time (something like 19 FPS), and pose detection at about 3 FPS. So in accordance with the holiday spirit, it knows when I am sleeping, and knows when I’m awake.

That was promising, but the NCS2 was marketed as allowing AI processing on edge computing devices. I set about installing it on the Raspberry Pi 3 Model B+ and compiling the application samples to see if it worked better than previous methods. This turned out to be more difficult than I expected, and the main goal of this article is to share the process I followed and save some of you a little frustration.

Continue reading “AI On Raspberry Pi With The Intel Neural Compute Stick” →

AI Patent Trolls Now On The Job For Drug Companies

January 30, 2019 by Dan Maloney 39 Comments

Love it or loathe it, the pharmaceutical industry is really good at protecting its intellectual property. Drug companies pour billions into discovering new drugs and bringing them to market, and they do whatever it takes to make sure they have exclusive positions to profit from their innovations for as long a possible. Patent applications are meticulously crafted to keep the competition at bay for as long as possible, which is why it often takes ages for cheaper generic versions of blockbuster medications to hit the market, to the chagrin of patients, insurers, and policymakers alike.

Drug companies now appear poised to benefit from the artificial intelligence revolution to solidify their patent positions even further. New computational methods are being employed to not only plan the synthesis of new drugs, but to also find alternative pathways to the same end product that might present a patent loophole. AI just might change the face of drug development in the near future, and not necessarily for the better.

Continue reading “AI Patent Trolls Now On The Job For Drug Companies” →

How To Make Your Own Springs For Extruded Rail T-Nuts

January 30, 2019 by Sonya Vasquez 24 Comments

Open-Source Extruded Profile systems are a mature breed these days. With Openbuilds, Makerslide, and Openbeam, we’ve got plenty of systems to choose from; and Amazon and Alibaba are coming in strong with lots of generic interchangeable parts. These open-source framing systems have borrowed tricks from some decades-old industry players like Rexroth and 80/20. But from all they’ve gleaned, there’s still one trick they haven’t snagged yet: affordable springloaded T-nuts.

I’ve discussed a few tricks when working with these systems before, and Roger Cheng came up with a 3D printed technique for working with T-nuts. But today I’ll take another step and show you how to make our own springs for VSlot rail nuts.

Continue reading “How To Make Your Own Springs For Extruded Rail T-Nuts” →

Now That’s What I Call Crypto: 10 Years Of The Best Of Bitcoin

January 29, 2019 by Brian Benchoff 18 Comments

On January 3rd, 2009, the Genesis Block was created. This was the first entry on the Bitcoin blockchain. Because of the nature of Bitcoin, all transactions lead back to this block. This is where Bitcoin began, almost exactly ten years ago.

The Genesis Block was created by Satoshi, a person or persons we know nothing about. In the decade since, we’ve seen the astonishing rise and meteoric descent of Bitcoin, and then it happened again after the bubble was re-inflated.

Due to the nature of Bitcoins, blockchains, and ledgers, the entire history of Bitcoin has been recorded. Every coin spent and every satoshi scrupled has been recorded for all to see. It’s time for a retrospective, and not just because I wanted to see some art based on the covers of Now That’s What I Call Music albums. No, ten years is a lot of stories to tell.

Continue reading “Now That’s What I Call Crypto: 10 Years Of The Best Of Bitcoin” →

Drone Sightings, A New British Comedy Soap Opera

January 28, 2019 by Jenny List 41 Comments

There’s a new soap opera that I can’t stop watching. Actually, I wish I could change the channel but this is unfortunately happening in real life. It’s likely the ups and downs of drone sightings would be too far fetched for fiction anyway.

If you aren’t British, maybe you will know a little of our culture through the medium of television. We don’t all live in stately homes like Downton Abbey of course, instead we’re closer to the sometimes comedic sets, bad lighting, and ridiculously complicated lives of the residents of Coronation Street or of Albert Square in Eastenders that you may have flashed past late at night on a high-number channel.

Our new comedy soap lacks the regional accents of Emmerdale or Hollyoaks, but has no less of the farce about it. Here at Hackaday we’ve brought you news of the UK’s peculiar habit of bad reporting and shoddy investigation of questionable drone sightings several times over the last year or two. Most recently we covered a series of events before Christmas that closed Gatwick, London’s second airport for several days over what turned out to be nothing of substance.

Unfortunately it didn’t end there. We’re back once more to catch up with the latest events down on the tarmac, and come away with a fresh set of reasonable questions unanswered by the popular coverage of the matter.

Continue reading “Drone Sightings, A New British Comedy Soap Opera” →

Circuit VR: Redundant Flip Flops And Voting Logic

January 25, 2019 by Al Williams 8 Comments

We are somewhat spoiled because electronics today are very reliable compared to even a few decades ago. Most modern electronics obey the bathtub curve. If they don’t fail right away, they won’t fail for a very long time, in all likelihood. However, there are a few cases where that’s not a good enough answer. One is when something really important is at stake — the control systems of an airplane, for example. The other is when you are in an environment that might cause failures. In those cases — near a nuclear reactor or space, for example, you often are actually dealing with both problems. In this installment of Circuit VR, I’ll show you a few common ways to make digital logic circuits more robust with some examples you can run in the Falstad simulator in your browser.

Continue reading “Circuit VR: Redundant Flip Flops And Voting Logic” →

Video: Putting High Speed PCB Design To The Test

January 24, 2019 by Bil Herd 48 Comments

Designing circuit boards for high speed applications requires special considerations. This you already know, but what exactly do you need to do differently from common board layout? Building on where I left off discussing impedance in 2 layer Printed Circuit Board (PCB) designs, I wanted to start talking about high speed design techniques as they relate to PCBs. This is the world of multi-layer PCBs and where the impedance of both the Power Delivery Network (PDN) and the integrity of the signals themselves (Signal Integrity or SI) become very important factors.

I put together a few board designs to test out different situations that affect high speed signals. You’ve likely heard of vias and traces laid out at right angles having an impact. But have you considered how the glass fabric weave in the board itself impacts a design? In this video I grabbed some of my fanciest test equipment and put these design assumptions to the test. Have a look and then join me after the break for more details on what went into this!