Coherent Quantum Learning trains parameterized quantum models by evolving a parameter superposition under a loss-encoding Hamiltonian, and toy simulations show probability concentrating at low-loss parameters.
hub
Training deep quantum neural networks
15 Pith papers cite this work, alongside 636 external citations. Polarity classification is still indexing.
15
Pith papers citing it
636
external citations · Crossref
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A new QNN architecture with unified graph, HAL, and ONNX pipeline enables cross-framework and cross-hardware QML with training time within 8% of native implementations and identical accuracy on Iris, Wine, and MNIST-4 tasks.
A finite-difference gradient inversion attack with adaptive low-pass filtering and Kalman acceleration reconstructs training inputs of small variational quantum neural networks from shared gradients when the model is over-parameterized.
A three-qubit recurrent quantum classifier using centroid-based similarity scores matches or beats several quantum baselines on four imbalanced fault datasets.
QFI-based regularization mitigates catastrophic forgetting in variational quantum classifiers, matching CFI-EWC in noiseless settings and retaining earlier tasks better under depolarizing noise.
CAQFM adds controlled quantum gates based on Pearson, Spearman, Kendall Tau, Mutual Information, and Distance Correlation measures to create richer feature maps, yielding higher accuracy than standard maps in VQC simulations on three benchmark datasets.
An iterative HHL algorithm with eigenvector continuation and complex scaling computes alpha-alpha resonance energies, converging in a handful of iterations in a simulated 8x8 model.
The paper defines QNN expressivity as the effective rank of the Fisher information matrix and shows numerically that this rank can reach its maximum 4^n-1 when data, measurement, and circuit are jointly optimized, then uses the rank as a reward for automated circuit design.
A systematic mapping study identifies ten architectural patterns, seven for the quantum-classical split and three for middleware, that describe how quantum components can be integrated into AI inference systems.
QTDE encodes higher-order topological structure into quantum states via evolution under the combinatorial Laplacian; on clique-complex benchmarks it edges out a Laplacian-comparison baseline only in easy, high-dimensional regimes, with QSVT-filter gains largely fitted.
A quantum neural network generates eigenvector-continuation basis states, and an iterative HHL routine solves the resulting generalized eigenvalue problem for the 4+ resonance of 9ΛBe.
A transformer front-end plus NSGA-II circuit search produces compact quantum classifiers that match or beat previous quantum models on Iris, Breast Cancer, MNIST (3 digits), and Heart Disease.
A survey of networked quantum services, from distributed quantum computers and cloud platforms to programming languages and standardization efforts.
A hybrid quantum-classical classifier using amplitude encoding and a variational circuit reports 82.2% fraud and 74.4% loan accuracy, but is evaluated without a train/test split and is outperformed by classical baselines.
A literature review that maps quantum neural network techniques to healthcare 5.0 applications, with a taxonomy, comparison tables, and a list of open challenges.
citing papers explorer
-
Quantum Hamiltonian Evolution for Coherent Quantum Learning
Coherent Quantum Learning trains parameterized quantum models by evolving a parameter superposition under a loss-encoding Hamiltonian, and toy simulations show probability concentrating at low-loss parameters.
-
Eliminating Vendor Lock-In in Quantum Machine Learning via Framework-Agnostic Neural Networks
A new QNN architecture with unified graph, HAL, and ONNX pipeline enables cross-framework and cross-hardware QML with training time within 8% of native implementations and identical accuracy on Iris, Wine, and MNIST-4 tasks.
-
A Numerical Gradient Inversion Attack in Variational Quantum Neural-Networks
A finite-difference gradient inversion attack with adaptive low-pass filtering and Kalman acceleration reconstructs training inputs of small variational quantum neural networks from shared gradients when the model is over-parameterized.
-
QSVM-RQNN: Low-Qubit Recurrent Quantum Similarity Learning for Condition Monitoring and Fault Classification
A three-qubit recurrent quantum classifier using centroid-based similarity scores matches or beats several quantum baselines on four imbalanced fault datasets.
-
Rethinking Quantum Continual Learning with Quantum Fisher Information
QFI-based regularization mitigates catastrophic forgetting in variational quantum classifiers, matching CFI-EWC in noiseless settings and retaining earlier tasks better under depolarizing noise.
-
A Correlation Aware Quantum Feature Map for Variational Quantum Classification
CAQFM adds controlled quantum gates based on Pearson, Spearman, Kendall Tau, Mutual Information, and Distance Correlation measures to create richer feature maps, yielding higher accuracy than standard maps in VQC simulations on three benchmark datasets.
-
Iterative Harrow-Hassidim-Lloyd quantum algorithm for solving resonances with eigenvector continuation
An iterative HHL algorithm with eigenvector continuation and complex scaling computes alpha-alpha resonance energies, converging in a handful of iterations in a simulated 8x8 model.
-
Learning to Maximize Quantum Neural Network Expressivity via Effective Rank
The paper defines QNN expressivity as the effective rank of the Fisher information matrix and shows numerically that this rank can reach its maximum 4^n-1 when data, measurement, and circuit are jointly optimized, then uses the rank as a reward for automated circuit design.
-
Architectural Patterns for Designing Quantum Artificial Intelligence Systems
A systematic mapping study identifies ten architectural patterns, seven for the quantum-classical split and three for middleware, that describe how quantum components can be integrated into AI inference systems.
-
Quantum Topological Data Encoding
QTDE encodes higher-order topological structure into quantum states via evolution under the combinatorial Laplacian; on clique-complex benchmarks it edges out a Laplacian-comparison baseline only in easy, high-dimensional regimes, with QSVT-filter gains largely fitted.
-
Studying few cluster resonances with quantum neural network driven iterative Harrow-Hassidim-Lloyd algorithm
A quantum neural network generates eigenvector-continuation basis states, and an iterative HHL routine solves the resulting generalized eigenvalue problem for the 4+ resonance of 9ΛBe.
-
Genetic Transformer-Assisted Quantum Neural Networks for Optimal Circuit Design
A transformer front-end plus NSGA-II circuit search produces compact quantum classifiers that match or beat previous quantum models on Iris, Breast Cancer, MNIST (3 digits), and Heart Disease.
-
Networked Quantum Services
A survey of networked quantum services, from distributed quantum computers and cloud platforms to programming languages and standardization efforts.
-
QFDNN: A Resource-Efficient Variational Quantum Feature Deep Neural Networks for Fraud Detection and Loan Prediction
A hybrid quantum-classical classifier using amplitude encoding and a variational circuit reports 82.2% fraud and 74.4% loan accuracy, but is evaluated without a train/test split and is outperformed by classical baselines.
-
A Study on Quantum Neural Networks in Healthcare 5.0
A literature review that maps quantum neural network techniques to healthcare 5.0 applications, with a taxonomy, comparison tables, and a list of open challenges.