The paper identifies measurement-induced logit contraction in hybrid QNNs and proposes Quantum Measurement Temperature, a learnable rescaling of bounded quantum outputs, to stabilize training and boost accuracy on fluorescence microscopy and Fashion MNIST data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mitigating Measurement-Induced Training Instability in Hybrid Quantum Neural Networks for Protein Classification
The paper identifies measurement-induced logit contraction in hybrid QNNs and proposes Quantum Measurement Temperature, a learnable rescaling of bounded quantum outputs, to stabilize training and boost accuracy on fluorescence microscopy and Fashion MNIST data.