Original image
Getty Images

A New Albanian Crisis

Original image
Getty Images

The First World War was an unprecedented catastrophe that killed millions and set the continent of Europe on the path to further calamity two decades later. But it didn’t come out of nowhere. With the centennial of the outbreak of hostilities coming up in 2014, Erik Sass will be looking back at the lead-up to the war, when seemingly minor moments of friction accumulated until the situation was ready to explode. He'll be covering those events 100 years after they occurred. This is the 85th installment in the series.

September 16, 1913: A New Albanian Crisis

In 1912 and 1913, a series of crises centered on Albania repeatedly brought Europe to the edge of war. Beginning in October 1912, Serbia conquered most of Albania in the First Balkan War, provoking an armed standoff between Serbia’s patron Russia and their shared enemy Austria-Hungary, which feared the rise of Serbian power and refused to allow the Slavic kingdom access to the sea. Austria-Hungary and Russia eventually agreed on a compromise and Europe’s Great Powers, meeting at the Conference of London, created a new, independent Albanian state in order to resolve the crisis.

In the second crisis, in May 1913, Serbia’s tiny sidekick, Montenegro, refused to give up its claim to the city of Scutari, even after the Great Powers granted the city to Albania. Austria-Hungary’s foreign minister, Count Berchtold (top), threatened military action against Montenegro, once again raising the possibility of a much broader conflict if Russia backed up Montenegro and Serbia. This crisis was peacefully resolved by a generous loan (read: bribe) from Britain and France, which helped Montenegro’s King Nikola see reason and withdraw from Scutari.

But this didn’t mean the Albanian situation was settled—far from it. Unsurprisingly, Serbia and Montenegro viewed Europe’s Great Powers as meddling bullies who stood in the way of their national aspirations, with Austria-Hungary, oppressor of their Slavic kinsmen, in the lead. In short, the Slavic kingdoms weren’t going to give up their claims to Albanian territory so easily (as demonstrated by the secret pact agreed by Serbia and Greece in May 1913, dividing Albania into Serbian and Greek spheres of influence).

In fact, the Serbians never completely withdrew from Albania, keeping some regular and paramilitary forces stationed in the mountainous interior on the pretext of controlling cross-border raids by Albanian bandits (which were a real issue). In early September 1913, Count Berchtold asked the other Great Powers to deliver another ultimatum to Serbia demanding withdrawal of the troops—but this time Russian foreign minister Sergei Sazonov (sensitive to criticism from pan-Slav ideologues who accused him of selling out their Slavic brethren in Serbia) refused to go along.   

The tension mounted on September 16, 1913, when Serbia’s acting Foreign Minister, Miroslav Spalajković, promised the Austrian charge d’affaires in Belgrade, Wilhelm Ritter von Storck, that the troops were being withdrawn from Albania. This was actually a bold-faced lie, as Serbian forces had only been ordered to withdraw as far as the River Drin, still well inside Albania territory. Storck (who had his own intelligence sources) knew it, and duly alerted Vienna to the deception.

Confronted with evidence of Serbian duplicity, and with any chance of concerted Great Powers diplomacy blocked by Russia, Austria-Hungary once again found itself with no option besides the threat of unilateral military action. Indeed, in some ways this was the most dangerous situation yet: By September 1913, the hawks in Vienna, led by chief of staff Franz Conrad von Hötzendorf, had converted Count Berchtold—who was increasingly frustrated with Serbian intransigence—to the cause of war against Serbia.

But there was still one key figure standing in the way: the heir to the throne, Archduke Franz Ferdinand, who correctly foresaw that an attack on Serbia would probably lead to war with Russia. According to the archduke the real enemy was Italy, a Great Power with its own claims on Austro-Hungarian territory, and Serbia was just a distraction. In the long run Franz Ferdinand hoped to solve the problem of Slavic nationalism by creating a third monarchy representing the Slavs—or even reforming the Dual Monarchy as a federal state with Serbia as a member. Of course the archduke’s plans for reform were bitterly opposed by the Hungarians, who stood to lose their decisive influence over imperial policy, as well as by the Serbs themselves, who jealously guarded their independence. 

Still, Franz Ferdinand, who’d been appointed inspector general of the armed forces by Emperor Franz Josef in August 1913, pressed ahead with his plans to attend the coming year’s military maneuvers in Bosnia, the empire’s main Slavic trouble spot. Thus, on September 16, 1913, the archduke (widely disliked by the imperial household for his brusque manner) bluntly informed Conrad that he intended to lead the maneuvers. This was bound to annoy Conrad, who always supervised the maneuvers himself and viewed Franz Ferdinand as a dilettante. But that was probably the point: The archduke, annoyed by Conrad’s advocacy of war with Serbia, was using the maneuvers to pull rank and put the chief of staff in his place. This little piece of political maneuvering would have unexpected, and profoundly tragic, consequences. 

See the previous installment or all entries.

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