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.