Computer ScienceNature Machine Intelligence
Closed-form continuous-time neural networks
R. Hasani, M. Lechner, et al.
This groundbreaking research by Ramin Hasani, Mathias Lechner, Alexander Amini, Lucas Liebenwein, Aaron Ray, Max Tschaikowski, Gerald Teschl, and Daniela Rus presents a closed-form approximation of liquid time-constant networks. The innovation significantly boosts training and inference speeds while preserving expressive power, revolutionizing spatiotemporal decision-making tasks with improved efficiency and scalability.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Computer Science
Memristor networks for real-time neural activity analysis
X. Zhu, Q. Wang, et al.
Earth Sciences
Universal neural networks for real-time earthquake early warning trained with generalized earthquakes
X. Zhang and M. Zhang
Engineering and Technology
Continuous estimation of power system inertia using convolutional neural networks
D. Linaro, F. Bizzarri, et al.
Computer Science
Biophysical neural adaptation mechanisms enable artificial neural networks to capture dynamic retinal computation
S. Idrees, M. B. Manookin, et al.
