Inverse design of optical needles with central zero-intensity points by artificial neural networks
Wei Xin, Qiming Zhang, Miṅ Gu
Abstract
Optical needles with central zero-intensity points have attracted much attention in the field of 3D super-resolution microscopy, optical lithography, optical storage and Raman spectroscopy. Nevertheless, most of the studies create few types of optical needles with central zero-intensity points based on the theory and intuition with time-consuming parameter sweeping and complex pre-select of parameters. Here, we report on the inverse design of optical needles with central zero-intensity points by dipole-based artificial neural networks (DANNs), permitting the creation of needles which are close to specific length and amplitude. The resolution of these optical needles with central zero-intensity points is close to axial diffraction limit (∼1λ). Additionally, the DANNs can realize the inverse design of several types on-axis distributions, such as optical needles and multifocal distributions.