MIT’s new ‘liquid’ neural network learns on the job — so robots can adapt to changing conditions
The system draws inspiration from a tiny worm
Future plans
The liquid network’s small number of highly expressive neurons also makes it easier to interpret its decisions.
“Just [by] changing the representation of a neuron, you can really explore some degrees of complexity you couldn’t explore otherwise,” said Hasani.
In tests, the network performed promisingly in predicting future values in datasets, ranging from atmospheric chemistry to traffic patterns.
Its small size also significantly reduced the computing costs.
Hasani said he now wants to prepare the system for real-world applications:
You can read the study paper on the pre-print serverarXiv.
Story byThomas Macaulay
Thomas is a senior reporter at TNW. He covers European tech, with a focus on AI, cybersecurity, and government policy.Thomas is a senior reporter at TNW. He covers European tech, with a focus on AI, cybersecurity, and government policy.
Get the TNW newsletter
Get the most important tech news in your inbox each week.
