Original image

Unexpected, Unwelcome Visitors

Original image

So I live in an apartment in a pretty reasonable neighborhood. But I get a constant flow of slightly weird people ringing my doorbell and wanting something, or being angry with me. Does this happen to everybody? Here's a rundown of some recent activity:

1. Oil Change Guy - a guy in overalls who knocked *and* rang my doorbell at 5:15pm, just after I'd walked up my stairs after returning home from work (had he been waiting around for me to come home?). I walked right back down the steps and opened the door. He wanted to sell me twenty oil changes at some local shop for the low-low price of $200. The deal was, I'd give him cash and he'd give me these vaguely suspicious-looking coupons. I agreed that it was a good price, but I really didn't expect to need twenty oil changes any time soon. And, too bad, I didn't have any cash on me. Plus: totally sketchy. He began bargaining, bringing the price down to $150, and finally to $80 -- and he wanted to walk with me to an ATM. His last line was, "That's only four bucks per oil change, bro!" I was forced to close the door on him.

2. Angry Marketing Lady - a lady in a business suit who rang my doorbell at 7am, angrily repeating the doorbell-ringing as I jumped to put on some halfway decent clothes. When I answered the door she said: "You're late! Jeez, I've been out here for ten minutes! This is not the way to start a marketing relationship." Now, I've never seen this lady before in my life, and I said something to that effect. She took another look at me -- with my bedhead and crumpled band tee shirt -- then asked, "Is this XYZ Produce Company?" I assured her that, indeed, I was not the one late for a marketing meeting with XYZ Produce Company. She left in a huff.

3. Blanket Dude - a gentleman who rang my doorbell at midnight and asked if he could borrow a blanket. (I nearly didn't answer the door, but figured he wouldn't be ringing it at midnight if he didn't need something.) I said, "You want to borrow it or have it?" He replied, "Have it." So I gave him a blanket, he made the sign of the cross, and he went on his way.

4. "The End is Nigh" Couple - a man and woman wearing matching beige suits and holding clipboards rang my doorbell at 2pm (while I was working from home). I had been getting these pamphlets through the mail slot for several days indicating that the world would be ending circa 2011, and encouraging me to buy a book that would explain what to do about it. (As I recall, the pamphlets had a lot of full-color illustrations of deer and other woodland creatures watching a nuclear blast in the distance.) When I answered the door, I found that this couple had been leaving them, and they were determined to speak to everyone in the neighborhood about this world-ending situation. The woman said, "Would you like to learn more about the End Times?" I had to close the door as she continued with her speech.

5. The Meat Salesman - this one actually happened back in the 90's, but it deserves a mention. I was living in Tallahassee with some school friends, and one evening this guy came to our door with a cardboard box filled with meat. Long story short, the guy claimed that he worked at some restaurant and had mistakenly ordered all this meat, and he had to sell it off pronto to avoid being fired. So his loss was our gain. He had a truck full of various kinds of meat, packed in these cardboard boxes and vacuum-sealed. My roommates proceeded to buy several hundred dollars' worth of meat from this entrepreneur. I declined. For what it's worth, the meat seemed okay and they did eat it all. I'm just not sure why anyone would want to buy hundreds of dollars of meat on a whim from a stranger.

So here's my question: who has come to your doorstep unannounced? Have you had any interesting scammers come by? Also: has anything good ever come from a random visitor?

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