AI & Tech
Liquid AI solves century-old neuroscience equation enabling scalable biological neural networks
Cognitive Revolution
Intelligence on the Edge: Liquid AI's Ramin Hasani on the Search for Device-Native Foundation Models
"1907, there was a scientist called Louis Lapicque that actually modeled the membrane potential, like how to model mathematically membrane potential kind of in, in, in cells. And that format of equation became like a fundamental of channel modeling. So 1907, this was Louis Lapicque's, um, kind of your membrane potential equation that is like an open differential equation. And then we have seen like some scientists called Hodgkin and Huxley, they, uh, they started working on really biological kind of grounding this type of differential equation. And then from there on, so that if in every textbook that you read, these type of formats of equations, they do not have a known closed-form solution, you know? And this format, like liquid neural networks, were also part of that type of equations. We, for the first time, we actually solved that."
In 2022, Liquid AI researchers achieved the first closed-form solution to neuronal dynamics equations that had remained unsolved since 1907. This mathematical breakthrough enabled scaling liquid neural networks from hundreds to potentially billions of neurons without numerical solvers, fundamentally changing what's computationally feasible with biologically-inspired architectures.
From this episode
Cognitive Revolution