Original image

The Longest Baseball Game Ever Played

Original image

Major League Baseball’s opening day, March 31, is approaching fast—but it’s the oft-overlooked minor leagues which witnessed one of the most improbable and historical games of all time. In a game which began on April 18, 1981, the Rochester Red Wings were eventually defeated by the Pawtucket Red Sox… after playing a record-shattering 33 innings. To this day, it remains the longest professional baseball game ever played.

It was a game rife with future superstars, as Hall-Of-Famers Cal Ripken Jr. and Wade Boggs played third base for Rochester and Pawtucket, respectively. That night, on the eve of Easter Sunday, 1740 fans were in attendance. At the time, the then-lengthiest game ever had been played between the Major League Brooklyn Dodgers and Boston Braves over 26 innings in 1920.

Nobody expected a pair of Minor League franchises to touch such a long-standing record. “When it went past that, I knew we were involved in something special,” said Pawtucket second baseman Marty Barrett of that fateful night.

A few innings earlier, at the bottom of the 21st, Boggs triumphantly scored a tying run after Rochester had pulled ahead to a 2-1 lead, only to be met with mixed reactions in the “PawSox” dugout. “A lot of people were saying ‘Yeah, yeah, we tied it, we tied, it!’” recalls Boggs. “And then they said, ‘Oh no, what did you do? We could have gone home!’”

Everyone eventually did go home at 4:09 AM the next morning, including the remaining 19 fans, by order of the league president himself. Yet, after 32 innings played in the taxing New England cold, the score was still tied, 2-2.

But the game still didn’t have a winner, so it was ultimately decided that the two teams would continue the game when next their schedules allowed it: over two months later on June 23rd. Since the Major Leaguers were on strike, and knowing that they were about to witness history in action, the fans turned out in droves—almost 5800 were in the stands. This time, however, they didn’t stay very long. In a mere 18 minutes, Barrett ran home to finally win the match and end the game.

A ball signed by members of both teams sits in the Baseball Hall of Fame to commemorate the event. A host of new records had been established, including most strikeouts (34 for Rochester) and most at-bats (114 for Pawtucket). An amazing 882 pitches had been thrown. Said Pawtucket manager Joe Morgan, “I wanted 40 innings so nobody could ever tie our beautiful record.” For more information on the legendary game, go here or check out Dan Barry’s excellent book, Bottom of the 33rd.

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