A CNN trained on simulated absorption images estimates Gaussian cold-atom cloud parameters as accurately as least-squares fitting, about 80 times faster, and from a single exposure.
These slices pass through the cloud center
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Learning for Absorption-Image Analysis
A CNN trained on simulated absorption images estimates Gaussian cold-atom cloud parameters as accurately as least-squares fitting, about 80 times faster, and from a single exposure.