Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures

Abstract

In quantum mechanics, a norm squared wave function can be interpreted as the probability density that describes the likelihood of a particle to be measured in a given position or momentum. This statistical property is at the core of the fuzzy structure of microcosmos. Recently, hybrid neural structures raised intense attention, resulting in various intelligent systems with far-reaching influence. Here, we propose a probability-density-based deep learning paradigm for the fuzzy design of functional meta-structures. In contrast to other inverse design methods, our probability-density-based neural network can efficiently evaluate and accurately capture all plausible meta-structures in a high-dimensional parameter space. Local maxima in probability density distribution correspond to the most likely candidates to meet the desired performances. We verify this universally adaptive approach in but not limited to acoustics by designing multiple meta-structures for each targeted transmission spectrum, with experiments unequivocally demonstrating the effectiveness and generalization of the inverse design.

Published in Research, an AAAS Science Partner Journal

References in corpus (9)

• Auto-Encoding Variational Bayes
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Learning to Plan Chemical Syntheses
• Outlook for inverse design in nanophotonics
• Improved Training of Wasserstein GANs
• Dielectric Optical Cloak
• Training deep neural networks for the inverse design of nanophotonic structures
• Wavefront Modulation and Subwavelength Diffractive Acoustics with an Acoustic Metasurface
• Stabilizing Training of Generative Adversarial Networks through Regularization

Cited by in corpus (7)

• Deep learning in nano-photonics: inverse design and beyond
• Controlling mass and energy diffusion with metamaterials
• Deep learning enabled design of complex transmission matrices for universal optical components
• Deterministic and probabilistic deep learning models for inverse design of broadband acoustic cloak
• Hybrid ultrathin metasurface for broadband sound absorption
• Acoustic Structure Inverse Design and Optimization Using Deep Learning
• Analog dual classifier via a time-modulated neuromorphic metasurface