A proof of concept that autoencoder and CNN classifiers can detect and classify four ultra-light dark matter signal models in simulated pulsar-timing residuals, with sensitivity several times worse than the one-step Bayesian benchmark.
Convolutional neural networks for the detection of the early inspiral of a gravitational-wave signal
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.HE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Neural Networks Hunting Ultra-Light Dark Matter
A proof of concept that autoencoder and CNN classifiers can detect and classify four ultra-light dark matter signal models in simulated pulsar-timing residuals, with sensitivity several times worse than the one-step Bayesian benchmark.