logo
ResearchBunny Logo
Al Pontryagin or how artificial neural networks learn to control dynamical systems

Computer Science

Al Pontryagin or how artificial neural networks learn to control dynamical systems

L. Böttcher, N. Antulov-fantulin, et al.

Discover Al Pontryagin, a pioneering neural ordinary differential equation framework developed by Lucas Böttcher, Nino Antulov-Fantulin, and Thomas Asikis. This innovative approach effectively learns control signals for steering complex dynamical systems towards desired states, showcasing remarkable potential in solving tough optimization challenges.

00:00
00:00
Playback language: English
Abstract
This paper introduces Al Pontryagin, a neural ordinary differential equation (NODE)-based control framework that learns control signals for steering high-dimensional dynamical systems toward desired target states within specific time intervals. It demonstrates Al Pontryagin's ability to learn control signals closely resembling those from optimal control frameworks, showcasing its potential for solving analytically and computationally intractable control and optimization problems.
Publisher
NATURE COMMUNICATIONS
Published On
Jan 17, 2022
Authors
Lucas Böttcher, Nino Antulov-Fantulin, Thomas Asikis
Tags
neural ordinary differential equations
control framework
dynamical systems
optimization problems
machine learning
control signals

Related Publications

Explore these studies to deepen your understanding of the subject.

Biophysical neural adaptation mechanisms enable artificial neural networks to capture dynamic retinal computation
Computer Science

Biophysical neural adaptation mechanisms enable artificial neural networks to capture dynamic retinal computation

S. Idrees, M. B. Manookin, et al.

Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data
Computer Science

Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data

C. H. Martin, T. (. Peng, et al.

Neural networks and physical systems with emergent collective computational abilities
Computer Science

Neural networks and physical systems with emergent collective computational abilities

J. J. Hopfield

To stay, remain or leave: how verbal concepts as response options in political referendums such as the Brexit polls might bias voting outcomes
Political Science

To stay, remain or leave: how verbal concepts as response options in political referendums such as the Brexit polls might bias voting outcomes

L. Ströbel, I. Koch, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny