Original image

My Favorite Documentaries: Burden of Dreams

Original image

First, a note to readers of last week's Sherman's March column: thank you! The comments have been fantastic, including almost 50 recommendations for documentaries. As a documentary junkie, I thank you for the fix -- and please continue to suggest your favorites in the comments!

This week I'll look at Les Blank's Burden of Dreams, a documentary from 1982. Special thanks to commenter Anthony Jr. for recommending this one -- I have it in my collection, but hadn't watched it in a long time.

Burden of Dreams follows German director Werner Herzog (another favorite of mine) as Herzog shoots his film Fitzcarraldo in the Peruvian jungle, and is constantly beset with problems. As Herzog faces each challenge, he maintains an unflappable (and at times bizarrely funny) stoic attitude, remaining completely committed to making his film. Herzog suggests early in the film that he is a man who lives for his dreams, and his dream during this documentary is to make Fitzcarraldo.

Much, much more (including video clips from YouTube) after the jump.

Herzog faces severe setbacks: his base camp is burned to the ground by angry locals, the production loses both its main actors (Jason Robards and Mick Jagger -- the latter left to record "Tattoo You"), a local war breaks out and forces the film to move over 1,000 miles to a new location, natives employed on the film crew are attacked by the warring tribes, and much, much more. One of my favorite parts of the film is about 49 minutes in, when the filmmakers show native workers eating lunch and discussing the wild warnings they've heard about working on the project. Watching these natives -- their body language, their manner of speaking, how easily they laugh together -- shows something universal about humanity. It doesn't matter that they're natives in Peru, deep in the jungle. They're people, and even at a remove of 25 years and an entire continent, I recognize them as totally cool people -- I'd love to hang out with them.

Here's a clip showing Herzog's monologue about the "obscenity of nature":

This documentary is about overcoming obstacles, about the Peruvian natives, and very much about Werner Herzog -- a man who seems almost unbelievably driven to achieve his dream. Much of the joy in this film is in watching Herzog narrate his struggles with a deadpan Teutonic delivery. He seems at once brilliant, driven, and possibly a little nutty. The subtext here is the simple question: why does Herzog suffer so much for this project? Watching the film, you'll get an answer from Herzog. You will understand what's important to Herzog, and see how he's operating at a deep level -- his life is truly dedicated to making films. This guy is hardcore.

Here's another clip from the movie, another snippet of an interview with Herzog commenting on the jungle ("We have to become humble in front of this overwhelming misery and overwhelming fornication, overwhelming growth, and overwhelming lack of order"):

Further reading: Criterion Collection essay, Les Blank's page on the film, and a Guardian Unlimited review. Or you can rent it from Netflix, rent it from Blockbuster, or buy it from Amazon (warning: it's spendy!).

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