How a tiny worm's brain could transform artificial intelligence

'Liquid neural networks', inspired by tiny worms, promise smaller, smarter and more transparent AI

- 

Today's artificial intelligence (AI) models are behemoths. Their function is determined by billions of parameters, they're trained on oceans of data and are hosted on vast, energy-hungry server farms. But does it have to be this way? Apparently not. One of the most promising new contenders for the future of machine intelligence grew out of something much smaller: a microscopic worm.

Inspired by Caenorhabditis elegans, a millimetre-long nematode with just 302 neurons in its nervous system, researchers have created a radically different kind of AI. Known as 'liquid neural networks', they can learn, adapt and reason all while running on a single device, instead of being distributed across many servers and the cloud.

"I wanted to understand human intelligence," Dr Ramin Hasani, co-founder and CEO of Liquid AI, a company at the forefront of this tiny revolution, told BBC Science Focus. “But when I started to look at what information we have available on the human brain, or even rat or monkey brains, I realised it’s almost nothing.”

At the time, the animal with the most comprehensively mapped nervous system was C. elegans. So that’s where Hasani and his colleagues started.

Hasani’s fascination with C. elegans wasn’t about its behaviour, but its ‘neural dynamics’ — the way its cells communicate.

Neurons in the worm’s brain communicate through graded, analogue signals rather than the electrical spikes more akin to digital signals found in larger animals. As nervous systems evolved and organisms grew bigger, spiking neurons became a more efficient way to send information.

Yet the roots of human neural computation still trace back to that analogue world.

For Hasani, this was a revelation. “Biology as a whole is a fascinating way to reduce the space of possibilities,” he said. “Billions of years of evolution have searched through all possible combinations of building efficient algorithms.”