Original image

These Ants Use Mercenaries to Fight for Them

Original image

In the jungles of Panama, a group of farmers ekes out a living by raising fungi for food. They’re peaceful, and when more aggressive neighbors come into their territory, looking for a cut of the crop, they oblige the guests and don’t fight them. While inconvenient, the arrangement pays off sometimes. When even more aggressive outsiders try to take over the farms, the first group of intruders earns their keep by repelling them and protecting their hosts. The not-exactly-welcome guests have their uses, and for the farmers, sharing a little fungus is a small price to pay for protection.

Humans have been using hired brutes to do their fighting for them for ages. Think of Blackwater Security, or Murder Inc., or Westeros’ most charming sellsword. But while the drama playing out in Central America echoes elements of Medieval history and The Magnificent Seven, none of the farmers, heroes, or villains here are people.

They’re ants.

The ants of the genus Sericomyrmex are peaceful farmers. They forage bits of vegetation, bring them back to their nests and grow fungus on them for food. Their lives aren’t all bucolic farmyard scenes in miniature, though. While many ants protect their colonies with specialized soldiers who can deliver powerful stings and bites, these six-legged agriculturalists are poorly armed, and can fight back only with their jaws. Unable to mount much of a defense against stinging foes, they’re regularly besieged by another ant species, Megalomyrmex symmetochus. Queens from this parasite species sneak into Sericomyrmex nests and form their own colonies within them, feeding on their hosts’ fungal crops, and sometimes their larva. They’ll also clip the wings of the virgin farmer queens, preventing them from forming new colonies and turning them into laborers. Instead of trying to fight the parasites and risk death, the farmers put up with them and supply them with room and board.

Biologists have found that the two groups are incredibly common with one another, and in some surveys, almost three quarters of Sericomyrmex nests are infested with Megalomyrmex. Even if they can’t fight back, why haven’t these farmers found some other way to rid themselves of their parasites?

One reason seems to be that the parasite is the lesser of two evils, and a good defense against an even bigger threat.

A third ant, Gnamptogenys hartmani, also raids the farmers’ colonies, taking over their gardens and nests and wiping out the inhabitants. The farmers are as defenseless against these pirates as they are against M. Symmetochus. G. hartmani has mastered a colony-conquering “agro-predator” lifestyle. Just two raiders can obliterate 70 percent of a Sericomyrmex colony, and the farmers that don’t perish usually flee and cede their home to the intruders.

When Gnamptogenys shows up at a Megalomyrmex-infested nest, though, the once unwelcome guest proves to be more of a help than a hindrance. The farmers will hide, while the more aggressive parasite soldiers confront and kill the invaders with their strong jaws and a little bit of chemical warfare. The Megalomyrmex ants possess a potent venom that they dole out through stings and by spraying into the air. It kills some of the raiders, and confuses others. The venom’s toxins appear to disrupt Gnamptogenys soldiers’ ability to recognize their nestmates, causing them to turn on each other and kill their own kind.

The arrangement hinges on a quirk of Megalomyrmex’s lifestyle. They don’t infest, eat, and move on like other parasites, but commit to a single host colony for life. Their success and survival depends on the farmers’ well-being.

To Rachelle Adams, an entomologist at the Smithsonian Institution whose research describes Megalomyrmex’s protective functions, the ants are more like mercenaries than pure parasites. They exploit their hosts, but that cost is compensated for by the defense they provide, and acting as soldiers for the farmers also protects their own interests. When trouble comes knocking, a parasitic win-lose relationship becomes a win-win.

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