A Quantum-Inspired Probabilistic Model for the Inverse Design of Meta-Structures
This work addresses the challenge of material engineering for researchers in computational design and photonics, offering an incremental improvement through a novel probabilistic approach.
The authors tackled the problem of inverse design for functional meta-structures by proposing a quantum-inspired probabilistic deep learning model, which accurately captures plausible designs and enriches choices by generating multiple meta-structures per targeted transmission spectrum.
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 microcosmos. Meanwhile, machine learning inverse design of materials raised intensive attention, resulting in various intelligent systems for matter engineering. Here, inspired by quantum theory, we propose a probabilistic deep learning paradigm for the inverse design of functional meta-structures. Our probability-density-based neural network (PDN) can accurately capture all plausible meta-structures to meet the desired performances. Local maxima in probability density distribution correspond to the most likely candidates. We verify this approach by designing multiple meta-structures for each targeted transmission spectrum to enrich design choices.