Original image

How Was Australia Populated?

Original image

It's one of anthropology's most enduring and controversial mysteries "“ no one is quite certain just how or when the indigenous peoples of Australia (also known as "aboriginals") arrived. As recently as the turn of the last century, it was believed that they had been on the continent no longer than 400 years or so. That eventually gave way to the notion that Aboriginals had been in Australia since about 8,000 years ago. Then in the 60s, a geologist named Jim Bowler uncovered the skeleton of a woman on the banks of a long-dried lake bed, who had died some 23,000 years ago. Nowadays, experts put the date of arrival from anywhere between 45,000 and
60,000 years ago.

That's where the trouble begins. Australia, as you probably already know, is an island; considered by some to be the world's largest, to be precise. It is surrounded by a not inconsiderable amount of water, the narrowest bits of which "“ like the Torres Strait in the north, between the top of Queensland and the bottom of Papua New Guinea "“ are dangerously rough and notoriously difficult to navigate. In general, human beings were not an oceangoing people prior to about 10-15,000 years ago, so the idea of people from what is now Indonesia crossing the Timor Sea in fishing rafts to populate the Northwestern coast of Australia is, needless to say, a problematic one. In his wonderful travel memoir In A Sunburned Country, Bill Bryson expresses this problem best:

"In order to put Homo sapiens in Australia you must accept that at a point in time so remote that it precedes the known rise of behaviorally modern humans there lived in southern Asia a people sufficiently advanced that they were fishing inshore waters from boats of some sort, rafts presumably. Never mind that the archaeological record shows no one else on earth doing this for another thirty thousand years.

Next we have to explain what led them to cross at least sixty miles of open sea to reach a land they could not know was there. The scenario that is invariably invoked is of a simple fishing raft "“ probably little more than a floating platform "“ accidentally carried out to sea, probably in one of the sudden squalls that are characteristic of this part of the world. The craft then drifted helplessly for some days before washing up on a beach in northern Australia. So far so good.

The question that naturally arises "“ but is seldom asked "“ is how you get a breeding stock out of this. If it's a lone fisherman who is carried off to Australia, then clearly he must find his way back to his homeland to report his discovery and to persuade enough people to come with him to start a colony. This suggests, of course, the possession of nautical skills sufficient to shuttle back and forth between invisible landmasses "“ a prowess few prehistorians are willing to grant. "¦ No one can possibly say. All that is certain is that Australia's indigenous peoples are there because their distant ancestors crossed at least sixty miles of fairly formidable sea tens of thousands of years before anyone else of earth dreamed of such an endeavor, and did it in sufficient numbers of begin to start the colonization of a continent. By any measure this is a staggeringly momentous accomplishment."

There is one other possible explanation, which the humorous and always-elegant Bryson fails to mention. Tasmania, Australia, Papua New Guinea and the patch of islands between the latter two all make up a single ancient continent, called Sahul, and as global sea levels rose and fell throughout the ice ages of the past 100,000 years, the forbidding straits of ocean between them occasionally disappeared, replaced by lush, tropical landbridges. In fact, it's thought that the now-underwater lowlands beneath the Torres Strait, between New Guinea and northern Australia, were a very popular place to live prior to about 10,000 years ago, when rising sea levels submerged them. (This is a very cool interactive site that allows you to check out the changing sea levels over time.)

Which is to say, at one time it was a bit simpler to get to Australia than Bryson lets on "“ though still not a cakewalk. It would have involved sailing (on planklike pseudo-rafts) from now-submerged islands on the eastern tip of Indonesia to now-submerged bits of what was western New Guinea "“ a distance certainly less than 60 miles.

Either way, the population of the Australian continent by humans remains a fascinating mystery.

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