Researchers Discover a More Flexible Approach to Machine Learning - Quanta Magazine

Ramin Hasani and Mathias Lechner, the driving forces behind the new design, realized years ago that C. elegans could be an ideal organism to use for figuring out how to make resilient neural networks that can accommodate surprise.

The millimeter-long bottom feeder is among the few creatures with a fully mapped-out nervous system, and it is capable of a range of advanced behaviors: moving, finding food, sleeping, mating and even learning from experience.

Mathias Lechner (left) and Ramin Hasani envisioned a new kind of flexible neural network based on the nervous system of the Caenorhabditis elegans worm.

While the algorithms at the heart of traditional networks are set during training, when these systems are fed reams of data to calibrate the best values for their weights, liquid neural nets are more adaptable.

“The main contribution here is that stability and other nice properties are baked into these systems by their sheer structure,” said Sriram Sankaranarayanan, a computer scientist at the University of Colorado, Boulder.

Apart from applications like autonomous driving and flight, liquid networks seem well suited to the analysis of electric power grids, financial transactions, weather and other phenomena that fluctuate over time.