Get the latest tech news
Liquid AI Is Redesigning the Neural Network
Inspired by microscopic worms, Liquid AI’s founders developed a more adaptive, less energy-hungry kind of neural network. Now the MIT spin-off is revealing several new ultraefficient models.
Liquid AI’s new models include one for detecting fraud in financial transactions, another for controlling self-driving cars, and a third for analyzing genetic data. In 2020, the researchers showed that such a network with only 19 neurons and 253 synapses, which is remarkably small by modern standards, could control a simulated self-driving car. "The benchmark results for their SLMs look very promising," says Sébastien Bubeck, a researcher at OpenAI who explores how AI models’ architecture and training affect their capabilities.
Or read this on Wired
