Eigentasks order noisy optical readout features by resolvability under noise, producing low-dimensional representations that improve few-shot classification by up to 10 percentage points over standard baselines in photon-limited regimes.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes realizing all-optical neural networks via phase-tunable interference, bad-cavity integration, and transient Rabi dynamics in waveguide QED, with simulations showing high accuracy on MNIST and object recognition.
citing papers explorer
-
Measurement-Adapted Eigentask Representations for Photon-Limited Optical Readout
Eigentasks order noisy optical readout features by resolvability under noise, producing low-dimensional representations that improve few-shot classification by up to 10 percentage points over standard baselines in photon-limited regimes.
-
Optical Neural Networks from Coherent Transient Dynamics in Waveguide QED
Proposes realizing all-optical neural networks via phase-tunable interference, bad-cavity integration, and transient Rabi dynamics in waveguide QED, with simulations showing high accuracy on MNIST and object recognition.