Abstract Machine learning (ML) has been remarkably successful in transforming numerous
scientific and technological fields in recent years including computer vision, natural …

The application of machine learning is demonstrated for rapid and accurate extraction of
plasmonic particles cluster geometries from hyperspectral image data via a dual variational …

Nanophotonics use the interaction between light and subwavelength structures to design
nanophotonic devices and to show unique optical, electromagnetic, and acoustic properties …

Neural network (NN)—based surrogates have been effectively used for modeling dynamic
systems, including photonic devices. However, black-box data-driven modeling approaches …

Typical topology optimization methods require complex iterative calculations, which cannot
be realized in meeting the requirements of fast computing applications. The neural network …

For the inverse design of metagratings and metasurfaces, generative deep learning has
been widely explored. Most of the works are based on a conditional generative adversarial …

We will present the recent progress of generative AI for the design of photonic devices,
including variable autoencoders and diffusion models, and latent space optimization. We …

Optically-active materials can be identified by their changeable optical signatures, allowing
for noncontact insights into the nanoscale behavior of the material and predicting its …