Gradient-free optimization of chaotic acoustics with reservoir computing
Francisco Huhn, Luca Magri
Abstract
The suppression of chaotic acoustic oscillations is a challenging problem in optimization. This is because gradient-based optimization struggles to optimize chaotic systems. In this paper, we develop a Bayesian approach based on reservoir computing to suppress chaotic oscillations without calculating the gradient.
Topics & Concepts
ChaoticChaotic systemsComputer scienceGradient methodBayesian optimizationAlgorithmArtificial intelligenceNeural Networks and Reservoir ComputingNeural Networks and ApplicationsNeural dynamics and brain function