ΑΙhub.org
 

Identifying light sources using machine learning

by
26 May 2020



share this:
photon counting set-up
Artistic impression of schematic experimental set-up for photon counting. The section in the light grey box corresponds to the thermal light part of the experiment and the section in the dark grey box corresponds to the coherent light part.

The identification of light sources is very important for the development of photonic technologies such as light detection and ranging (LiDAR), and microscopy. Typically, a large number of measurements are needed to classify light sources such as sunlight, laser radiation, and molecule fluorescence. The identification has required collection of photon statistics or quantum state tomography. In recently published work, researchers have used a neural network to dramatically reduce the number of measurements required to discriminate thermal light from coherent light at the single-photon level.

In their paper, authors from Louisiana State University, Universidad Nacional Autónoma de México and Max-Born-Institut describe their experimental and theoretical techniques. They demonstrate the potential of machine learning to perform discrimination of light sources at extremely low light levels. This is achieved by training single artificial neurons with the statistical fluctuations that characterize coherent and thermal states of light.

The experimental set-up involves a continuous wave (CW) laser that is divided by a 50:50 beam splitter. Half of the beam passes through optical components which generate pseudo-thermal light. The emerging photons are counted by a superconducting nanowire single-photon detector (SNSPD). The other half of the beam is used as a coherent light source and is detected by another SNSPD. The data are divided in time bins of 1µs; this timeframe corresponds to the coherence time of the laser. The equipment is tuned so that the mean number of photons counted in each bin is below one.

The distributions of photon counts obtained from repeated runs of this experiment were used to train and test an ADALINE neuron and, for comparison, naive Bayes classifier. ADALINE is a single-layer neural network model based on a linear processing element, proposed by Bernard Widrow, for binary classification. It has no hidden layers, simply consisting of inputs and an output neuron.

The researchers also tested different machine learning methods: a) one-dimensional convolutional neural network (1D CNN) and b) a multilayer neural network (MNN). Interestingly, they found that these more sophisticated methods did not significantly affect the classification. They concluded that a simple ADALINE offers a perfect balance between accuracy and simplicity.

The team believe that their work has important implications for multiple photonic technologies, such as LiDAR and microscopy of biological materials. Using their method fewer measurements are needed for classification, enabling researchers to identify light sources much more quickly. In certain applications, such as microscopy, this means that they can limit light damage since they don’t have to illuminate the sample nearly as many times when taking measurements.

Read the research in full

Identification of light sources using machine learning
Chenglong You, Mario A. Quiroz-Juárez, Aidan Lambert, Narayan Bhusal, Chao Dong, Armando Perez-Leija, Amir Javaid, Roberto de J. León-Montiel, and Omar S. Magaña-Loaiza
Applied Physics Reviews (2020)

The work is also posted on arXiv.




Lucy Smith , Managing Editor for AIhub.
Lucy Smith , Managing Editor for AIhub.




            AIhub is supported by:


Related posts :



Harnessing AI for a climate-resilient Africa: An interview with Amal Nammouchi, co-founder of AfriClimate AI

We spoke to Amal about how AfriClimate AI started, and the projects and initiatives that the team are focussing on.
05 November 2024, by

Forthcoming machine learning and AI seminars: November 2024 edition

A list of free-to-attend AI-related seminars that are scheduled to take place between 4 November and 31 December 2024.
04 November 2024, by

The Machine Ethics podcast: Socio-technical systems with Lisa Talia Moretti

In this episode Ben chats to Lisa about data and AI literacy, data governance, ethical frameworks, and more.
01 November 2024, by

Building trust in AI: Transparent models for better decisions

AI is becoming a part of our daily lives, from approving loans to diagnosing diseases. But if we can't understand the decisions the models output, how can we trust them?
31 October 2024, by

Congratulations to the #ECAI2024 outstanding paper award winners

Find out which articles won the ECAI and PAIS 2024 awards.
30 October 2024, by

AIhub monthly digest: October 2024 – Nobel Prizes, the AI Song Contest, and towards safe and reliable AI agents

Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
29 October 2024, by




AIhub is supported by:






©2024 - Association for the Understanding of Artificial Intelligence


 












©2021 - ROBOTS Association