Next-Value Prediction of Beam Waists From Mixed Pitch Grating Using Simplified Transformer Model

In this study, a simplified transformer model is used to predict the beam waist of 1,092 nm light coupled out from SiN-based mixed pitch gratings at various heights. The beam waists data at various heights above the grating is first compiled. Then, we used a sequence of the current beam waist values...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Dian Lim, Peng Zhao, Luca Guidoni, Jean-Pierre Likforman, Chuan Seng Tan
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10634767/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417378202386432
author Yu Dian Lim
Peng Zhao
Luca Guidoni
Jean-Pierre Likforman
Chuan Seng Tan
author_facet Yu Dian Lim
Peng Zhao
Luca Guidoni
Jean-Pierre Likforman
Chuan Seng Tan
author_sort Yu Dian Lim
collection DOAJ
description In this study, a simplified transformer model is used to predict the beam waist of 1,092 nm light coupled out from SiN-based mixed pitch gratings at various heights. The beam waists data at various heights above the grating is first compiled. Then, we used a sequence of the current beam waist values, z-positions, and the computed mathematical indicators (features) to predict the next beam waist value (labels). Optimized transformer model yields average percentage error (APE) of 6.6% between the predicted and actual beam waists, which corresponds to 93.4% prediction accuracy. This study provides a pioneering approach to using natural language processing model to perform predictive modelling on photonics data, and possible extrapolation of photonics data using transformer model.
format Article
id doaj-art-44cdfdddd6c54e28b81f34026d82d3b2
institution Kabale University
issn 1943-0655
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-44cdfdddd6c54e28b81f34026d82d3b22025-08-20T03:32:51ZengIEEEIEEE Photonics Journal1943-06552024-01-011651910.1109/JPHOT.2024.344216910634767Next-Value Prediction of Beam Waists From Mixed Pitch Grating Using Simplified Transformer ModelYu Dian Lim0https://orcid.org/0000-0003-4188-997XPeng Zhao1https://orcid.org/0000-0002-4850-9354Luca Guidoni2https://orcid.org/0000-0002-7175-8471Jean-Pierre Likforman3https://orcid.org/0000-0002-8879-7813Chuan Seng Tan4https://orcid.org/0000-0003-1250-9165School of Electrical and Electronics Engineering, Nanyang Technological University, SingaporeInteruniversity Microelectronics Centre (IMEC), Leuven, BelgiumLaboratoire Matériaux et Phénomènes Quantiques (MPQ), Université de Paris, Paris, FranceLaboratoire Matériaux et Phénomènes Quantiques (MPQ), Université de Paris, Paris, FranceSchool of Electrical and Electronics Engineering, Nanyang Technological University, SingaporeIn this study, a simplified transformer model is used to predict the beam waist of 1,092 nm light coupled out from SiN-based mixed pitch gratings at various heights. The beam waists data at various heights above the grating is first compiled. Then, we used a sequence of the current beam waist values, z-positions, and the computed mathematical indicators (features) to predict the next beam waist value (labels). Optimized transformer model yields average percentage error (APE) of 6.6% between the predicted and actual beam waists, which corresponds to 93.4% prediction accuracy. This study provides a pioneering approach to using natural language processing model to perform predictive modelling on photonics data, and possible extrapolation of photonics data using transformer model.https://ieeexplore.ieee.org/document/10634767/Attentiongratingsmulti-head attentionphotonics integrated circuitsquantum computingself-attention
spellingShingle Yu Dian Lim
Peng Zhao
Luca Guidoni
Jean-Pierre Likforman
Chuan Seng Tan
Next-Value Prediction of Beam Waists From Mixed Pitch Grating Using Simplified Transformer Model
IEEE Photonics Journal
Attention
gratings
multi-head attention
photonics integrated circuits
quantum computing
self-attention
title Next-Value Prediction of Beam Waists From Mixed Pitch Grating Using Simplified Transformer Model
title_full Next-Value Prediction of Beam Waists From Mixed Pitch Grating Using Simplified Transformer Model
title_fullStr Next-Value Prediction of Beam Waists From Mixed Pitch Grating Using Simplified Transformer Model
title_full_unstemmed Next-Value Prediction of Beam Waists From Mixed Pitch Grating Using Simplified Transformer Model
title_short Next-Value Prediction of Beam Waists From Mixed Pitch Grating Using Simplified Transformer Model
title_sort next value prediction of beam waists from mixed pitch grating using simplified transformer model
topic Attention
gratings
multi-head attention
photonics integrated circuits
quantum computing
self-attention
url https://ieeexplore.ieee.org/document/10634767/
work_keys_str_mv AT yudianlim nextvaluepredictionofbeamwaistsfrommixedpitchgratingusingsimplifiedtransformermodel
AT pengzhao nextvaluepredictionofbeamwaistsfrommixedpitchgratingusingsimplifiedtransformermodel
AT lucaguidoni nextvaluepredictionofbeamwaistsfrommixedpitchgratingusingsimplifiedtransformermodel
AT jeanpierrelikforman nextvaluepredictionofbeamwaistsfrommixedpitchgratingusingsimplifiedtransformermodel
AT chuansengtan nextvaluepredictionofbeamwaistsfrommixedpitchgratingusingsimplifiedtransformermodel