Original image

Two More Odd Things I Just Learned About Fish

Original image

When I'm not blogging for mental_floss, I can usually be found wearing bright orange rubber pants and gutting, cutting and selling fish at my local Whole Foods (and winning awards for it). Sometimes, my two worlds collide and I find some scientific research involving my ocean-dwelling friends that begs for a blog post. This is one of those times.

1. Dying Zebrafish Give Their Kids a Powerup
Many animals give off biochemical signals when they're frightened or hurt to warn other members of the species of danger and elicit anti-predator and defensive behavior. The effects of these "alarm substances" on juvenile and adult animals have been the subject of many studies, but researchers at the Marine Biology and Ecology Research Center at the University of Plymouth wanted to know how embryos still in the early stages of development would respond to the substances. [1]

Embryos of two species (Danio albolineatus and D. rerio) of zebrafish, tropical freshwater members of the minnow family native to southeastern Himalayan region, were exposed to skin injury-induced alarm substances from adults of the species and filmed during development. The development time of both species was sped up, and alarm substance-exposed embryos reached their first muscular contractions (D. rerio) and their first heartbeats (D. rerio and D. albolineatus) earlier than control embryos.

The exposure to the alarm substance caused the embryos to developed a functional heartbeat almost 10%, or 1.5 to 2 hours, faster than normal. That might seem like a snail's pace to us, but after fertilization, zebrafish develop precursors to all the major organs within 36 hours, hatch within 48 hours and begin swimming and feeding within 72 hours. Speeding up development by even just an hour reduces the time the embryos are vulnerable in their egg case and possibly not under the guard of their parents.

How will these developmental advances affect the fish later in life? The researchers think they could either be a sign of an increased development rate overall (with the fish rushing through all their developmental stages), or they could relate to later physiological or behavioral traits.

2. Stingrays Are Smarter Than They Look
rayFreshwater stingrays, the tropical river-dwelling relatives of ocean-going stingrays, have, like sharks and other cartilaginous fish, long been thought of as reflexive machines without cognitive capacity and ability (in part because they're difficult to study). Well, we owe them an apology, because they recently joined a very special club: the royal order of animals that use tools.

In an experiment, researchers from the Hebrew University of Jerusalem in Israel designed a plastic tube test apparatus with two openings and placed a piece of food in it.[2] All five of their stingray subjects (Potamotrygon castexi) figured out how to get the food out of the tube with a carefully directed jet of water (which meets the basic definition of a tool), the first indication of tool use in the batoid fishes. That's one small step for understanding the evolutionary origins of cognitive function in higher vertebrates and one giant leap for raykind. Congrats, guys.

[1] S. Mourabit, S. D. Rundle, J. I. Spicer and K. A. Sloman. "Alarm substance from adult zebrafish alters early embryonic development in offspring." Biology Letters. DOI:10.1098/rsbl.2009.0944

[2] M. J. Kuba, R. A. Byrne and G. M. Burghardt."A new method for studying problem solving and tool use in stingrays." Animal Cognition. DOI: 10.1007/s10071-009-0301-5


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