• Corpus ID: 239615982

Intelligent metaphotonics empowered by machine learning

  title={Intelligent metaphotonics empowered by machine learning},
  author={Sergey Krasikov and Aaron D. Tranter and Andrey Bogdanov and Yuri S. Kivshar},
Sergey Krasikov, 2, ∗ Aaron Tranter, Andrey Bogdanov, and Yuri Kivshar 2, † School of Physics and Engineering, ITMO University, St. Petersburg 197101, Russia Nonlinear Physics Center, Research School of Physics, Australian National University, Canberra ACT 2601, Australia Centre for Quantum Computation and Communication Technology, Department of Quantum Science, Research School of Physics, The Australian National University, Canberra, ACT 2601, Australia (Dated: October 25, 2021) 

Figures from this paper

Experimental realization of the active convolved illumination imaging technique for enhanced signal-to-noise ratio
Wyatt Adams, Anindya Ghoshroy, and Durdu Ö. Güney3∗ Ansys, Inc., 2600 Ansys Dr, Canonsburg, PA 15317, USA Caltech Optical Imaging Laboratory, Andrew and Peggy Cherng Department of Medical Engineering


Approaching the adiabatic timescale with machine learning
This work experimentally demonstrates a general approach using a machine-learning algorithm that develops a model of the system, based on previous performance, to create further educated guesses on how to improve, and reaches a speed faster than that of previous approaches, dealing well with the complex dynamics and experimental imperfections present with its empirical approach.
Multiparameter optimisation of a magneto-optical trap using deep learning
A deep artificial neural network is implemented to optimise the magneto-optic cooling and trapping of neutral atomic ensembles, showing an improvement in the resulting resonant optical depth compared to more traditional solutions.
Explainable Machine Learning for Scientific Insights and Discoveries
This article provides a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas and discusses three core elements that were identified as relevant in this context: transparency, interpretability, and explainability.
Machine Prediction of Topological Transitions in Photonic Crystals
It is found that the trained network yields remarkably accurate predictions of the topological phases for 1D photonic crystals, even for the geometric and material parameters that are outside of the range of the trained dataset.
Fast machine-learning online optimization of ultra-cold-atom experiments
It is demonstrated that the Gaussian process machine learner is able to discover a ramp that produces high quality BECs in 10 times fewer iterations than a previously used online optimization technique.
A high-bias, low-variance introduction to Machine Learning for physicists
The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, generalization, and gradient descent before moving on to more advanced topics in both supervised and unsupervised learning.
Inverse design of photonic topological state via machine learning
This work focuses on Zak phases, which are the topological properties of one-dimensional photonics crystals, and proposes an approach to achieve the design of optical structures with the target topological states by exploiting machine learning technologies.
Machine learning at the energy and intensity frontiers of particle physics
The application and development of machine-learning methods used in experiments at the frontiers of particle physics (such as the Large Hadron Collider) are reviewed, including recent advances based on deep learning.
Interpretable inverse design of particle spectral emissivity using machine learning
This work demonstrates the possibility for approachable and interpretable machine learning models to be used for rapid forward and inverse design of devices that span a broad and diverse parameter space.
Optimisation of colour generation from dielectric nanostructures using reinforcement learning.
The colour generation by dielectric nanostructures is investigated and it is shown that this model can find geometrical properties that can generate much purer red, green and blue colours compared to previously reported results.