AI & Tech
Liquid AI CEO reveals 12-neuron network can autonomously park cars
Cognitive Revolution
Intelligence on the Edge: Liquid AI's Ramin Hasani on the Search for Device-Native Foundation Models
"Early on the results were fascinating. Like we saw that with 12 neurons, with actually 12 neurons, you could parallel park autonomously like a car, like a small car. With 19 neurons, you could drive a car. With 30 neurons, you can fly autonomously like navigating kind of a drone."
Ramin Hassani describes how MIT research into biologically-inspired liquid neural networks achieved remarkable control tasks with tiny neuron counts—12 for parking, 19 for driving, 30 for drone navigation. These differential equation-based systems mimic C. elegans worm brain dynamics and dramatically outperform traditional neural networks in efficiency and out-of-distribution generalization for robotics applications.
From this episode
Cognitive Revolution