Researchers Discover a More Flexible Approach to Machine Learning

Artificial intelligence researchers have celebrated a string of successes with neural networks, computer programs that roughly mimic how our brains are organized. But despite rapid progress, neural networks remain relatively inflexible, with little ability to change on the fly or adjust to unfamiliar circumstances.

In 2020, two researchers at the Massachusetts Institute of Technology led a team that introduced a new kind of neural network based on real-life intelligence—but not our own. Instead, they took inspiration from the tiny roundworm, Caenorhabditis elegans, to produce what they called liquid neural networks. After a breakthrough last year, the novel networks may now be versatile enough to supplant their traditional counterparts for certain applications.

Liquid neural networks offer “an elegant and compact alternative,” said , a roboticist at the University of California,