Original image

The Weekend Links

Original image

"¢ From Kevin, an amazing, giant beautiful moth from Australia. Personally, I think moths are underrated, and often more intriguing than their fragile fellow fliers, the butterfly.

"¢ Catastic! Cats who look just like Wilford Brimley. Also check out this video game hack for the ultimate Wilford Brimley experience.

"¢ Hmmm, what do horror-punkers read? Take a look into the wild world of Glenn Danzig's book collection ... narrated by Danzig himself. (Thanks Pat for this jewel.)

"¢ Ron Burgundy interviews Tom Brokaw. (Via The Daily Tube, home of The Best New Videos on the Internet.)

"¢ Here are 10 cool cloud formations you may not have seen. I was lucky enough to witness #2 on this list, Mammatous Clouds, the other evening. Stunning. But then again, I'm a weather nerd.

"¢ Also from Kevin, an in depth look at whether our brains change when we go into space.

"¢ An Indiana Jones sports quiz from Page 2. Only serious fans of both need apply. The questions left me baffled, but I applaud anyone who can score well.

"¢ If you're looking for listening material, Bill Simmons recently welcomed Chuck Klosterman to The B.S. Report podcast. Chuck never responded to our internship offer.

"¢ One of the funniest things I've read in quite some time ... Jack Handey graces The New Yorker's "Shouts and Murmurs" feature with a fantastic piece.

"¢ Anyone excited for the Stanley Cup Finals? If you're watching and Detroit fans start tossing octopuses on the ice, here's a brief explanation:

"Every sport has its own strange traditions. I'd argue hockey's 'throwing an octopus on the ice for good luck' is the weirdest. Tossing the eight-tentacled cephalopod was the brainchild of Detroit storeowners Pete & Jerry Cusimano. The date: April 15, 1952. The logic: one tentacle for each of the eight victories it took to win the Stanley Cup back then. Later that spring, most likely fueled by the good luck octopus, the Red Wings won the title. PETA has objected to this practice, which continues to this day. The Red Wings mascot is not a Red Wing, but Al the Octopus."

"¢ From Flossy reader Tony, another great article: 10 Things You Didn't Know about Ol' Blue Eyes, Frank Sinatra.

"¢ A series of pictures documenting what happens when eggs freeze. Something I hadn't ever really considered, but the results are eggshellent.


"¢ From Jason: "I'm on some pretty strange mailing lists. Usually the non-bills & magazines go straight from the mailbox to the trash. But this one intrigued me enough to call on the floss army for an explanation. Anyone speak...whatever language this is? What's going on here? My money's on 'root beer ad.'"

[Update: Miss Cellania is on the same strange mailing list.)

"¢ A plethora of links this week from Angie. First: How do you add up? Here's a 1930s "wife rating chart" to be thankful at how far we've come.

An incredible video made with a Mac OSX Leopard desktop by digital filmmaker Dennis Liu.

"¢ Number 234879 in the list of Great Inventions: Transparent Post-Its!

"¢ Finally, the Lovely Picture of the Week.

Thanks as always to everyone who sent in such great links this week! Clean out your favorites list, drum up some shameless plugs, or just send forth any linkage to Have a great long weekend!

[Last Weekend's Links]

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
Name the Author Based on the Character
May 23, 2017
Original image