Plasmonic colours predicted by deep learning

Baxter, Joshua; Lesina, Antonino Calà; Guay, Jean‐Michel; Weck, Arnaud; Berini, Pierre; Ramunno, Lora

doi:10.1038/s41598-019-44522-7

Cited by 84 publications

(56 citation statements)

References 20 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…gaining popularity. Several developments in ML over the past few years has motivated the researchers to explore its potential in the field of photonics, including multimode fibers [5], power splitter [6], plasmonics [7], grating coupler [8], photonic crystals [9], [10], metamaterials [11], photonic modes fields distribution [12], label-free cell classification [13], molecular biosensing [14], optical communications [15], [16] and networking [17], [18].…”

mentioning

confidence: 99%

Machine Learning Regression Approach to the Nanophotonic Waveguide Analyses

Chugh

Ghosh

Gulistan

et al. 2019

J. Lightwave Technol.

View full text Add to dashboard Cite

Machine learning is an application of artificial intelligence that focuses on the development of computer algorithms which learn automatically by extracting patterns from the data provided. Machine learning techniques can be efficiently used for a problem with a large number of parameters to be optimized and also where it is infeasible to develop an algorithm of specific instructions for performing the task. Here, we combine the finite element simulations and machine learning techniques for the prediction of mode effective indices, power confinement and coupling length of different integrated photonics devices. Initially, we prepare a dataset using COMSOL Multiphysics and then this data is used for training while optimizing various parameters of the machine learning model. Waveguide width, height, operating wavelength, and other device dimensions are varied to record different modal solution parameters. A detailed study has been carried out for a slot waveguide structure to evaluate different machine learning model parameters including number of layers, number of nodes, choice of activation functions, and others. After training, this model is used to predict the outputs for new input device specifications. This method predicts the output for different device parameters faster than direct numerical simulation techniques. Absolute percentage error of less than 5% in predicting an output has been obtained for slot, strip and directional waveguide coupler designs. This study pave the step towards using machine learning based optimization techniques for integrated silicon photonics devices. Index Terms-Machine learning, neural networks, regression, multilayer perceptron, silicon photonics. I. INTRODUCTION M ACHINE learning (ML) technology is being extensively used in many aspects of modern society: web searches, social networking, smartphones, bioinformatics, robotics, chatbots, and self-driving cars [1]. ML techniques are used to classify or detect objects in images, speech to text conversion, pattern recognition, natural language processing, sentiment analysis and recommendations of products/movies for users based on their search preferences. ML algorithms can be trained to perform exceptionally well when it is difficult to analyze the underlying physics and mathematics of the problem [2]. ML algorithms extract patterns from the raw data provided during the training without being explicitly programmed. The learned patterns can be used to make predictions on some other data of interest. ML systems can be trained more efficiently when massive amount of data is present [3], [4]. Recently, research on the application of ML techniques for optical communication systems and nanophotonic devices is

show abstract

mentioning

confidence: 99%

Machine Learning Regression Approach to the Nanophotonic Waveguide Analyses

Chugh

Ghosh

Gulistan

et al. 2019

J. Lightwave Technol.

View full text Add to dashboard Cite

show abstract

“…Following a distinct approach, aiming to obtain optimized responses, one may focus on bilayer structures and play with the choice of the ferromagnetic material and the metallic capping layer, both having deep impacts on the thermoelectric conversion efficiency. In this case, it is well known that capping-layer materials with high spin-orbit coupling are the main elected for investigations of spintronics effects [21]. This fact is justified given that they enable the interconversion between charge current and spin current [5].…”

Section: Introductionmentioning

confidence: 99%

Modulating the Spin Seebeck Effect in Co2FeAl Heusler Alloy for Sensor Applications

Lopes

Souza

Santos

et al. 2020

Sensors

View full text Add to dashboard Cite

The thermoelectric conversion technique has been explored in a broad range of heat-flow sensors. In this context, the Spin Seebeck Effect emerges as an attractive candidate for biosensor applications, not only for the sensibility improvement but also for the power-saving electronic devices development. Here, we investigate the Longitudinal Spin Seebeck Effect in films with a Co 2 FeAl/W bilayer structure grown onto GaAs (100) substrate, systems having induced uniaxial magnetic anisotropy combined with cubic magnetic anisotropy. From numerical calculations, we address the magnetic behavior and thermoelectric response of the films. By comparing experiment and theory, we explore the possibility of modulating a thermoelectric effect by magnetic anisotropy. We show that the thermoelectric voltage curves may be modulated by the association of magnetic anisotropy induction and experimental parameters employed in the LSSE experiment.

show abstract

“…Recently, machine and deep learning have risen to the forefront in many fields such as computer vision, robotics, chatbots, natural language processing, among others. Over the past few years, researchers have also explored the application of machine learning in the field of photonics including multimode fibers [16], plasmonics [17], metamaterials [18], biosensing [19], metasurface design [20,21], optical communications [22] and networking [23]. Kiarashinejad et al [24] proposed a deep learning-based algorithm using the dimensionality reduction technique to understand the properties of electromagnetic wave-matter interaction in nanostructures.…”

Section: Introductionmentioning

confidence: 99%

Machine learning approach for computing optical properties of a photonic crystal fiber

et al. 2019

View full text Add to dashboard Cite

Photonic crystal fibers (PCFs) are the specialized optical waveguides that led to many interesting applications ranging from nonlinear optical signal processing to high-power fiber amplifiers. In this paper, machine learning techniques are used to compute various optical properties including effective index, effective mode area, dispersion and confinement loss for a solid-core PCF. These machine learning algorithms based on artificial neural networks are able to make accurate predictions of above mentioned optical properties for usual parameter space of wavelength ranging from 0.5-1.8 μm, pitch from 0.8-2.0 μm, diameter by pitch from 0.6-0.9 and number of rings as 4 or 5 in a silica solid-core PCF. We demonstrate the use of simple and fast-training feed-forward artificial neural networks that predicts the output for unknown device parameters faster than conventional numerical simulation techniques. Computation runtimes required with neural networks (for training and testing) and Lumerical Mode Solutions are also compared.

show abstract

Plasmonic colours predicted by deep learning

Cited by 84 publications

References 20 publications

Machine Learning Regression Approach to the Nanophotonic Waveguide Analyses

Machine Learning Regression Approach to the Nanophotonic Waveguide Analyses

Modulating the Spin Seebeck Effect in Co2FeAl Heusler Alloy for Sensor Applications

Machine learning approach for computing optical properties of a photonic crystal fiber

Contact Info

Product

Resources

About