Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of Light

Abstract Advancements in optical quantum technologies have been enabled by the generation, manipulation, and characterization of light, with identification based on its photon statistics. However, characterizing light and its sources through single photon measurements requires efficient detectors an...

Full description

Saved in:
Bibliographic Details
Main Authors: Mahesh Bhupati, Abhishek Mall, Anshuman Kumar, Pankaj K. Jha
Format: Article
Language:English
Published: Wiley-VCH 2025-02-01
Series:Advanced Physics Research
Subjects:
Online Access:https://doi.org/10.1002/apxr.202400089
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850252660686454784
author Mahesh Bhupati
Abhishek Mall
Anshuman Kumar
Pankaj K. Jha
author_facet Mahesh Bhupati
Abhishek Mall
Anshuman Kumar
Pankaj K. Jha
author_sort Mahesh Bhupati
collection DOAJ
description Abstract Advancements in optical quantum technologies have been enabled by the generation, manipulation, and characterization of light, with identification based on its photon statistics. However, characterizing light and its sources through single photon measurements requires efficient detectors and longer measurement times to obtain high‐quality photon statistics. Here, a deep learning‐based variational autoencoder (VAE) method is introduced for classifying single photon added coherent state (SPACS), single photon added thermal state (SPATS), and mixed states between coherent and SPACS as well as between thermal and SPATS of light. The semi‐supervised learning‐based VAE efficiently maps the photon statistics features of light to a lower dimension, enabling quasi‐instantaneous classification with low average photon counts. The proposed VAE method is robust and maintains classification accuracy in the presence of losses inherent in an experiment, such as finite collection efficiency, non‐unity quantum efficiency, finite number of detectors, etc. Additionally, leveraging the transfer learning capabilities of VAE enables successful classification of data of any quality using a single trained model. It is envisioned that such a deep learning methodology will enable better classification of quantum light and light sources even in poor detection.
format Article
id doaj-art-77210cb8b75544f8bb14cb3c6c52063f
institution OA Journals
issn 2751-1200
language English
publishDate 2025-02-01
publisher Wiley-VCH
record_format Article
series Advanced Physics Research
spelling doaj-art-77210cb8b75544f8bb14cb3c6c52063f2025-08-20T01:57:35ZengWiley-VCHAdvanced Physics Research2751-12002025-02-0142n/an/a10.1002/apxr.202400089Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of LightMahesh Bhupati0Abhishek Mall1Anshuman Kumar2Pankaj K. Jha3Laboratory of Optics of Quantum Materials (LOQM) Department of Physics Indian Institute of Technology Bombay Powai Mumbai 400076 IndiaMax Planck Institute for the Structure and Dynamics of Matter Hamburg 22761 GermanyLaboratory of Optics of Quantum Materials (LOQM) Department of Physics Indian Institute of Technology Bombay Powai Mumbai 400076 IndiaQuantum Technology Laboratory 〈Q|T|L〉 Department of Electrical Engineering and Computer Science Syracuse University Syracuse NY 13210 USAAbstract Advancements in optical quantum technologies have been enabled by the generation, manipulation, and characterization of light, with identification based on its photon statistics. However, characterizing light and its sources through single photon measurements requires efficient detectors and longer measurement times to obtain high‐quality photon statistics. Here, a deep learning‐based variational autoencoder (VAE) method is introduced for classifying single photon added coherent state (SPACS), single photon added thermal state (SPATS), and mixed states between coherent and SPACS as well as between thermal and SPATS of light. The semi‐supervised learning‐based VAE efficiently maps the photon statistics features of light to a lower dimension, enabling quasi‐instantaneous classification with low average photon counts. The proposed VAE method is robust and maintains classification accuracy in the presence of losses inherent in an experiment, such as finite collection efficiency, non‐unity quantum efficiency, finite number of detectors, etc. Additionally, leveraging the transfer learning capabilities of VAE enables successful classification of data of any quality using a single trained model. It is envisioned that such a deep learning methodology will enable better classification of quantum light and light sources even in poor detection.https://doi.org/10.1002/apxr.202400089deep learningspacsspatsvariational autoencoder
spellingShingle Mahesh Bhupati
Abhishek Mall
Anshuman Kumar
Pankaj K. Jha
Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of Light
Advanced Physics Research
deep learning
spacs
spats
variational autoencoder
title Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of Light
title_full Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of Light
title_fullStr Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of Light
title_full_unstemmed Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of Light
title_short Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of Light
title_sort deep learning based variational autoencoder for classification of quantum and classical states of light
topic deep learning
spacs
spats
variational autoencoder
url https://doi.org/10.1002/apxr.202400089
work_keys_str_mv AT maheshbhupati deeplearningbasedvariationalautoencoderforclassificationofquantumandclassicalstatesoflight
AT abhishekmall deeplearningbasedvariationalautoencoderforclassificationofquantumandclassicalstatesoflight
AT anshumankumar deeplearningbasedvariationalautoencoderforclassificationofquantumandclassicalstatesoflight
AT pankajkjha deeplearningbasedvariationalautoencoderforclassificationofquantumandclassicalstatesoflight