A hybrid quantum-classical pipeline pairs signature kernel feature layers with QCNNs for binary MNIST digit classification, finding modest accuracy gains for some ansatzes but VQLS-based kernel computation is infeasible beyond 5-6 time steps.
Time-series forecasting with deep learning: a survey.Philo- sophical Transactions of the Royal Society A, 379(2194):20200209, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
QCNN with Rough Path Signature Kernels
A hybrid quantum-classical pipeline pairs signature kernel feature layers with QCNNs for binary MNIST digit classification, finding modest accuracy gains for some ansatzes but VQLS-based kernel computation is infeasible beyond 5-6 time steps.