An AI for deciphering what animals do all day

April 30, 2018 by Kim Martineau, Columbia University
Researchers show how an algorithm for filtering spam can learn to pick out, from hours of video footage, the full behavioral repertoire of tiny, pond-dwelling Hydra. In the above image, hydra's neurons are labeled with a green fluorescence indicator. Credit: Yuste Lab, Columbia University

Much of what biologists have learned about animal behavior over the years has come from careful observation and painstaking notes. There could soon be an easier way.

In a new study in the journal eLife, researchers at Columbia University show how an algorithm for filtering spam can learn to pick out, from hours of video footage, the full behavioral repertoire of tiny, pond-dwelling Hydra. A close relative of coral, jellies and sea anemones, Hydra is so primitive that it lacks a backbone or brain. But when it moves, feeds and evades predators, it behaves in predictable ways that a computer can recognize.

By comparing Hydra's behaviors to the firing of its , the researchers hope to eventually understand how its nervous system, and that of more complex animals, works. "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 the study's senior author, Rafael Yuste, a neuroscientist at Columbia University and a member of Columbia's Data Science Institute. "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."

Hydra's ancestors appeared on Earth some 700 million years ago, before the Cambrian explosion that gave rise to most modern species. Instead of a brain, hundreds of neurons run along its narrow, translucent body coordinating behaviors that range from basic—curling into a ball to avoid predators—to sophisticated—somersaulting to get around.

When researchers manipulated Hydra's environmental conditions, they found that six common behaviors, captured in the above movie, hardly changed at all. Credit: Yuste Lab/Columbia University

In an earlier study in Current Biology, Yuste and his colleagues recorded all of its neurons firing in real-time and discovered four sets of neural circuits that control four distinct elongation and bending behaviors, paving the way to understand how Hydra's nervous system regulates its behavior.

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 researchers think Hydra may have evolved a way of adjusting to its environment as if on auto-pilot. They are now experimenting with other stimuli to see if Hydra will respond and learn. Eventually, they hope to crack its neural code with a model that shows how its networks of neurons create .

The time-lapse image above shows Hydra moving through a somersault, its main form of locomotion. Credit: Yuste Lab/Columbia University

Lessons learned from Hydra may also be useful to a branch of engineering concerned with maintaining stability and precise control in machines, from ships to planes, navigating in highly variable conditions.

The nervous systems of even simple animals like Hydra have evolved to maintain constancy in their behaviors, said Yuste. If engineers could unlock their secret, technology could be infused with biologically-inspired controls that have evolved over hundreds of millions of years.

"Reverse engineering Hydra has the potential to teach us so many things," said the study's lead author, Shuting Han, a graduate student at Columbia.

Formerly in Yuste's lab, the study's other authors, Ekaterina Taralova and Christophe Dupre, are now at the startup Zoox Inc. and Harvard.

Explore further: Seeing without eyes: Hydra stinging cells respond to light

More information: Comprehensive machine learning analysis of Hydra behavior reveals a stable basal behavioral repertoire, eLife, DOI: 10.7554/eLife.32605.001

Related Stories

Seeing without eyes: Hydra stinging cells respond to light

March 4, 2012

In the absence of eyes, the fresh water polyp, Hydra magnipapillata, nevertheless reacts to light. They are diurnal, hunting during the day, and are known to move, looping end over end, or contract, in response to light. ...

Hydra can modify its genetic program

November 23, 2015

Champion of regeneration, the freshwater polyp Hydra is capable of reforming a complete individual from any fragment of its body. It is even able to remain alive when all its neurons have disappeared. Researcher the University ...

How hydras know where to regrow lost body parts

February 7, 2017

Few animals can match the humble hydra's resilience. The small, tentacled freshwater animals can be literally shredded into pieces and regrow into healthy animals. A study published February 7 in Cell Reports suggests that ...

Scientists discover 600 million-year-old origins of vision

March 11, 2010

By studying the hydra, a member of an ancient group of sea creatures that is still flourishing, scientists at UC Santa Barbara have made a discovery in understanding the origins of human vision. The finding is published in ...

Pluto's moon Hydra

July 14, 2015

In 1930, Pluto was observed for the first time. For many decades, astronomers thought that the "ninth planet of the Solar System" was a solitary object. But by 1978, astronomers discovered that it also had a moon roughly ...

Recommended for you

Fluid dynamics may play key role in evolution of cooperation

May 22, 2018

Believe it or not—it's in our nature to cooperate with one another, even when cheating may be more profitable. Social cooperation is common in every scale of life, from the simplest bacterial films and multicellular tissues ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.