Original image

Let Public Radio Talk You Through the Financial Crisis

Original image

Over the past few months, some exciting (perhaps heart-stopping) action has played out on the world financial stage. There's a credit crunch, a mortgage crisis, commercial paper is frozen, banks are failing, and T-notes are the new mattresses. What does it all mean? I admit, I know nothing about finance, and hearing the increasingly dire news reports wasn't really helping to break it down in terms that I could follow. Until I discovered what's happening over at National Public Radio and Public Radio International. If you're wondering about the financial situation, I've got links below to help you learn about it -- in a way that human beings can understand.

The first salvo from public radio's crisis-explaining squad came on May 9. On that evening's All Things Considered program, PRI's This American Life Producer Alex Blumberg (who sounds uncannily like Ira Glass, but isn't) teamed up with NPR Business and Economics Correspondent Adam Davidson to deliver a thirteen-minute piece called Global Pool of Money Got Too Hungry. This was presented in a much longer (and better) form on This American Life as The Giant Pool of Money. The latter is the best explanation I've heard of global finance, including what exactly is going on with these crazy mortgages: what they are, how they're bundled, how money changes hands on a global scale, and why the mortgage system was so crazy. So your first assignment is to listen to The Giant Pool of Money (you can click the "Full Episode" link on the left of the page to launch the free player). Trust me, you'll be fascinated, and you'll learn a lot. Warning: Ira Glass has a really scratchy voice on this episode. Fortunately he pretty much leaves it up to Blumberg and Davidson to narrate the actual story.

Last week, This American Life followed up with Another Frightening Show About the Economy (here's a direct MP3 link). This show explained the US market bailout/rescue plan, and delved further into topics like credit default swaps, commercial paper, regulation (or the lack thereof), and toxic assets.

Honestly, this episode was even more interesting than the previous explanation of the global economy -- probably because it's so topical; we all want to know exactly what the Paulson Plan is, whether it's a good idea, and exactly how bad the whole situation is. Changes are coming fast and furious, and the information in this program is less than a week old. Now is the time to listen.

Planet MoneyIn addition to the aforementioned hour-long programs, Blumberg, Davidson, and friends have created a blog and podcast called Planet Money. The blog is updated many (MANY!) times daily, and the podcast is updated every few days. It's extremely topical stuff. Recorded at the end of the business day in New York, the podcast features interviews with economists and traders, and it's hosted by producers who can actually explain the financial jargon. For the layperson, the podcast is the best source I've found to explain the financial crisis. The blog is good too, but there's so much content there that it almost seems daunting. Anyway, check out the Planet Money blog, and if you're a podcast listener (and really, why shouldn't you be? You don't need an iPod...), I strongly recommend the Planet Money podcast. It's currently the top podcast on iTunes, and guess who's second? This American Life.

Note that if you don't want to subscribe to the podcast, you can browse through the episodes using iTunes and just double-click an episode to listen to it.

So where do you get your news on the financial situation? Or are you just hiding in a bunker, waiting for it all to pass? Share your finds and fears in the comments. (Keep in mind that you can post URLs as long as you leave off the 'http' business.)

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