CLOSE
Original image

A Profile of a Profile of Charlie Kaufman

Original image

Charlie Kaufman is the writer behind movies including Adaptation, Being John Malkovitch, and Eternal Sunshine of the Spotless Mind. (He also wrote two episodes of the TV classic Get a Life, though he didn't win any Oscars for them.) In the leadup to Kaufman's directorial debut Synecdoche, New York, Wired decided to write a profile of the man -- because the Wired folks, like me, are huge fans. In true Kaufman style, the Wired editors decided to add a layer to the story: document the process of writing the profile during the writing of the profile.

So, despite not having actually interviewed Kaufman (yet), Wired writers have been posting daily to a blog called Storyboard, currently featuring nine entries (including a fairly dry video of a staff meeting). The stated idea is to provide a look inside the process of writing a profile, but if Kaufman's writing is any guide, watch for the Storyboard blog to go off the rails -- and fast. Just as Kaufman's Adaptation was ostensibly an adaptation of Susan Orlean's The Orchid Thief, the movie is in fact a crazy mixture of a drug caper and a think piece about trying to adapt a book about flowers (which, lacking much action, is hard to do...hence the drug caper). More than that, Adaptation an examination of identity and time and evolution and sex and frustration and storytelling. The result is transformative and wonderful -- one of my very favorite movies ever -- but it's a very different text from The Orchid Thief. (Which itself is an entertaining and enlightening read.)

Anyway, Wired's Storyboard blog currently features behind-the-scenes material from various editors talking about scheduling interviews with Kaufman and various other people in his circle (Spike Jonze, Michel Gondry, and so on). But the text of the blogs seems to suggest (to me, at least) that this is all a set-up for the kind of meta-narrative for which Kaufman is famous. Here's a sample from Jason Tanz's post on August 29:

2) this threatens to become REALLY corny, but: a) if Kaufman's project [Synecdoche, New York] is "emotional truth," and he thinks that the standard storytelling tropes (and commercial imperatives) obscure that truth; and b) my job is to present some "truth" about Kaufman; then c) there's some parallel between the movie and the article (or really any creative project, I guess). It will be a challenge to bring the meta without also bringing the obnoxious, but maybe there's a theme to touch lightly upon there.

3) the dude doesn't like to talk about his personal life, which is fair enough, and doesn't like to explain his work, which is also fair enough. I haven't hear him talk much about his influences, which would seem a pretty good place to start. I'm assuming like Borges, Kafka, Dick (he wrote an early adaptation of Scanner, Darkly), etc. I don't want to overdo the recluse angle, which has been done to death already.

Stay tuned, folks. For Kaufman fans, this is about to get interesting.

Original image
iStock // Ekaterina Minaeva
technology
arrow
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
quiz
arrow
Name the Author Based on the Character
May 23, 2017
Original image
SECTIONS
BIG QUESTIONS
BIG QUESTIONS
WEATHER WATCH
BE THE CHANGE
JOB SECRETS
QUIZZES
WORLD WAR 1
SMART SHOPPING
STONES, BONES, & WRECKS
#TBT
THE PRESIDENTS
WORDS
RETROBITUARIES