CLOSE
Original image

Wonderful things from the Times book review section, #1

Original image

The novelist Richard Powers had an article this weekend about dictating, rather than writing, literary works. There's sparkly trivia in it, which I'll share in a bit, but first I have a question: Powers is arguing that when it comes to writing things down, "you'd be hard-pressed to invent a greater barrier to cognitive flow." As a reporter, though, I've often found that people are surprised at how clumsy their off-the-cuff speech is and, on reading their own quotes in an article, often want to write in something more mellifluous instead. That seems to go directly against what Powers is saying. Thoughts, anyone? Are people more eloquent or less when they speak, as opposed to when they write? And where does the old advice to "write like you talk" come in?

Anyway, on to the trivia:

For most of history, most reading was done out loud. Augustine remarks with surprise that Bishop Ambrose could read without moving his tongue. Our passage into silent text came late and slow, and poets have resisted it all the way. From Homer to hip-hop, the hum is what counts. Blind Milton chanted "Paradise Lost" to his daughters. Of his 159-line "Tintern Abbey," Wordsworth said, "I began it upon leaving Tintern ... and concluded ... after a ramble of four or five days. ... Not a line of it was altered, and not any part of it written down till I reached Bristol." Wallace Stevens used to compose while walking to work, then dictate the results to his secretary, before proceeding to his official correspondence as vice president of the Hartford insurance company. ...

Even novelists, working in a form so very written, have needed to write by voice. Stendhal dictated "The Charterhouse of Parma" in seven weeks. An impoverished Dostoyevsky had just six weeks to deliver the manuscript of "The Gambler" or face complete ruin. He hired a stenographer, knocked the book out in four weeks, then married the girl. ...

Once, while dictating "Finnegans Wake" to Beckett, Joyce is said to have answered a knock on the door; Beckett dutifully jotted down his "Come in." Surprised by the transcript, a delighted Joyce let it ride.

Legend claims that the astoundingly prolific William Vollmann once tried speech recognition software while suffering from repetitive stress injury. He sat down to write his folks. "Dear Mom and Dad" came out as the much more Vollmannesque "The man is dead."

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