A convolutional autoencoder with an information-ordered bottleneck reconstructs complex FRB dynamic spectra better than PCA and maps real bursts onto a continuous morphology space.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.HE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Representation learning for fast radio burst dynamic spectra
A convolutional autoencoder with an information-ordered bottleneck reconstructs complex FRB dynamic spectra better than PCA and maps real bursts onto a continuous morphology space.