Skip to main content

Spam filters and AI help figure out what animals do all day

The pond-dwelling Hydra is not a very complex little animal but it does have a complex repertoire of moves that aren’t clear until after extensive human observation. Examining these moves took a long time and scientists were never sure that they had seen all of them. Now, thanks to an algorithm used to catch spam, researchers have been able to catalog all of the Hydra’s various moves, allowing them to map those moves to the neurons firing in its weird little head.

“People have used machine learning algorithms to partly analyze how a fruit fly flies, and how a worm crawls, but this is the first systematic description of an animal’s behavior,” said Rafael Yuste, a neuroscientist at Columbia University. “Now that we can measure the entirety of Hydra’s behavior in real-time, we can see if it can learn, and if so, how its neurons respond.”

Luckily, the little Hydra was pretty predictable. From the report:

In the current study, the team went a step further by attempting to catalog Hydra’s complete set of behaviors. To do so, they applied the popular “bag of words” classification algorithm to hours of footage tracking Hydra’s every move. Just as the algorithm analyzes how often words appear in a body of text to pick out topics (and flag, for example, patterns resembling spam), it cycled through the Hydra video and identified repetitive movements.

Their algorithm recognized 10 previously described behaviors, and measured how six of those behaviors responded to varying environmental conditions. To the researchers’ surprise, Hydra’s behavior barely changed. “Whether you fed it or not, turned the light on or off, it did the same thing over and over again like an Energizer bunny,” said Yuste.

The system used to map the Hydra’s reactions can be used to map more complicated systems. The researchers essentially “reverse-engineered” the Hydra and may be able to use the technique to “maintain stability and precise control in machines, from ships to planes, navigating in highly variable conditions.”

“Reverse engineering Hydra has the potential to teach us so many things,” said Shuting Han, a graduate student at Columbia.



from Startups – TechCrunch https://ift.tt/2HG64s7

Comments

Popular posts from this blog

Thousands of cryptocurrency projects are already dead

Two sites that are actively cataloging failed crypto projects, Coinopsy and DeadCoins , have found that over a 1,000 projects have failed so far in 2018. The projects range from true abandonware to outright scams and include BRIG , a scam by two “brothers,” Jack and Jay Brig, and Titanium , a project that ended in an SEC investigation. Obviously any new set of institutions must create their own sets of rules and that is exactly what is happening in the blockchain world. But when faced with the potential for massive token fundraising, bigger problems arise. While everyone expects startups to fail, the sheer amount of cash flooding these projects is a big problem. When a startup has too much fuel too quickly the resulting conflagration ends up consuming both the company and the founders and there is little help for the investors. These conflagrations happen everywhere are a global phenomenon. Scam and dead ICOs raised $1 billion in 2017 with 297 questionable startups in the mix. The

Dance launches its e-bike subscription service in Berlin

German startup Dance is launching its subscription service in its hometown Berlin. For a flat monthly fee of €79 (around $93 at today’s exchange rate), users will get a custom-designed electric bike as well as access to an on-demand repair and maintenance service. Founded by the former founders of SoundCloud and Jimdo , the company managed to raise some significant funding before launching its service. BlueYard led the startup’s seed round while HV Capital (formerly known as HV Holtzbrinck Ventures) led Dance’s €15 million Series A round, which represented $17.7 million at the time. E-bike subscription service Dance closes $17.7M Series A, led by HV Holtzbrinck Ventures The reason why Dance needed so much capital is that the company has designed its own e-bike internally. Called the Dance One, it features an aluminum frame and weighs around 22kg (48.5lb). It has a single speed and it relies on its electric motor to help you go from 0 to 25kmph. And the best part is that you