A variational autoencoder learns quantum embeddings compressing ImageNet into 13 qubits and achieving 98.5% accuracy on MNIST 3-vs-5 classification with a quantum circuit, close to classical baselines and far above naive amplitude embeddings.
author Bromley, T.R
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
H-SemiS decomposes multi-class KOA severity grading into binary sub-tasks in a semi-supervised setup with self-supervision and quantum-inspired mixing, outperforming baselines on two multi-class and two binary datasets.
Staged KD from a frozen classical visual encoder enables shallow VQC heads to learn non-trivial policies on CartPole Pixels and Acrobot Pixels where direct pixel-to-VQC training is harder.
citing papers explorer
-
Tailor Made Embeddings for Quantum Machine Learning
A variational autoencoder learns quantum embeddings compressing ImageNet into 13 qubits and achieving 98.5% accuracy on MNIST 3-vs-5 classification with a quantum circuit, close to classical baselines and far above naive amplitude embeddings.
-
Staged Hybridisation for Visual Quantum Reinforcement Learning via Knowledge Distillation
Staged KD from a frozen classical visual encoder enables shallow VQC heads to learn non-trivial policies on CartPole Pixels and Acrobot Pixels where direct pixel-to-VQC training is harder.