Abstract A recurring weakness in quantum machine learning (QML) is that reported ‘quantum advantages’ are seldom tested against a capacity-matched classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it. Our primary contribution is methodological: a protocol for attributing such gains honestly—a capacity-matched classical bottleneck of identical parameter budget, transparent reporting of where quantum does not help, and validation on real quantum hardware—which we develop and apply through a concrete case study. That case study is Quantum Adaptive Self-Attention (QASA), a hybrid Transformer that replaces the value projection of a single encoder layer with a 36-parameter parameterized quantum circuit (PQC), keeping all other layers classical. Across nine synthetic benchmarks and the real-world ETTh1 dataset, QASA improves on a full-capacity classical Transformer for chaotic and trend-dominated signals. To ask whether this is a genuinely quantum effect, we introduce a control rarely applied in QML—a capacity-matched classical bottleneck with the same parameter budget—and find that it matches the PQC on the error metrics. The gain is therefore attributable to the low-rank value-projection bottleneck (an architectural parsimony principle), not to quantumness; adding further quantum layers only degrades performance and trainability. We accordingly position the quantum layer not as a source of accuracy advantage but as a competitive instantiation of this principle: its low-rank compression onto the signal’s intrinsic dimensionality is matched by a classical bottleneck, so the gain is architectural rather than quantum. The quantum layer’s distinguishing features are physical—a high circuit entanglement (Meyer–Wallach Q = 0.981 with only 27 CNOTs, which we report as a circuit-level property) and, most concretely, noisy intermediate-scale quantum deployability, which we verify by executing the trained model on a real IBM Quantum processor (one-step prediction within 7.5 % of noiseless simulation on the quantum-favored task and 25 % , with overlapping error bars, on a classical-favored control; no error mitigation). Relative to other quantum sequence models (quantum long short-term memory (QLSTM), QnnFormer), QASA is moreover the most resource-efficient of the three: it reaches competitive accuracy with the fewest quantum parameters (36 vs 90–128) and the strongest entanglement-per-gate ( Q = 0.981 with 27 CNOTs vs QLSTM’s 56), and retains trainable gradients that deeper circuits lose. We argue that capacity-matched baselines and honest reporting of where quantum does not help are prerequisites for credible quantum-machine-learning claims.
Abstract A recurring weakness in quantum machine learning (QML) is that reported ‘quantum advantages’ are seldom tested against a capacity-matched classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it. Our primary contribution is methodological: a protocol for attributing such gains honestly—a capacity-matched classical bottleneck of identical parameter budget, transparent reporting of where quantum does not help, and validation on real quantum hardware—which we develop and apply through a concrete case study. That case study is Quantum Adaptive Self-Attention (QASA), a hybrid Transformer that replaces the value projection of a single encoder layer with a 36-parameter parameterized quantum circuit (PQC), keeping all other layers classical. Across nine synthetic benchmarks and the real-world ETTh1 dataset, QASA improves on a full-capacity classical Transformer for chaotic and trend-dominated signals. To ask whether this is a genuinely quantum effect, we introduce a control rarely applied in QML—a capacity-matched classical bottleneck with the same parameter budget—and find that it matches the PQC on the error metrics. The gain is therefore attributable to the low-rank value-projection bottleneck (an architectural parsimony principle), not to quantumness; adding further quantum layers only degrades performance and trainability. We accordingly position the quantum layer not as a source of accuracy advantage but as a competitive instantiation of this principle: its low-rank compression onto the signal’s intrinsic dimensionality is matched by a classical bottleneck, so the gain is architectural rather than quantum. The quantum layer’s distinguishing features are physical—a high circuit entanglement (Meyer–Wallach Q = 0.981 with only 27 CNOTs, which we report as a circuit-level property) and, most concretely, noisy intermediate-scale quantum deployability, which we verify by executing the trained model on a real IBM Quantum processor (one-step prediction within 7.5 % of noiseless simulation on the quantum-favored task and 25 % , with overlapping error bars, on a classical-favored control; no error mitigation). Relative to other quantum sequence models (quantum long short-term memory (QLSTM), QnnFormer), QASA is moreover the most resource-efficient of the three: it reaches competitive accuracy with the fewest quantum parameters (36 vs 90–128) and the strongest entanglement-per-gate ( Q = 0.981 with 27 CNOTs vs QLSTM’s 56), and retains trainable gradients that deeper circuits lose. We argue that capacity-matched baselines and honest reporting of where quantum does not help are prerequisites for credible quantum-machine-learning claims.
Abstract Quantum machine learning (QML) has attracted growing interest because quantum states and circuits may provide new representational primitives for learning, yet progress remains constrained by noisy intermediate-scale quantum (NISQ) hardware and heterogeneous evaluation practices. This article presents a critical review of recent QML architectures and representative empirical and theoretical studies, with emphasis on work published since 2022 alongside selected seminal references. To improve comparability, “quantum advantage” is assessed in three distinct senses: computational scaling under stated input-access assumptions, empirical predictive performance in the benchmark setting considered, and resource efficiency at a fixed budget accounting for both classical compute and quantum execution, including shot costs. Organized by architecture family and application domain, the review analyzes how baseline strength, hyperparameter optimization, preprocessing, and budget reporting shape conclusions. Overall, quantum feature maps and kernels, as well as variational (often hybrid) pipelines, can be competitive on selected small- to medium-scale benchmarks, but robust end-to-end evidence for a general practical advantage remains limited. Reported gains are often sensitive to budget matching and may be dominated by measurement overheads, dataset and preprocessing effects, and training instabilities. The review concludes that credible progress requires standardized benchmarking, transparent end-to-end resource accounting, and hardware-centered evaluations that test scalability and robustness beyond toy regimes.
Quantum machine learning (QML) promises new representational and computational capabilities, yet practical deployment on near-term hardware is hampered by resource overheads, depth constraints, and fragile trainability. This thesis advances resource-aware QML by proposing architectures and kernels that retain expressivity while sharply reducing qubit counts, circuit depth, and entangling-gate budgets. The work is presented in an article-based format with three core contributions. First, I introduce a Coherent Feed-Forward Quantum Neural Network (CFF-QNN) that preserves quantum coherence across all layers, mirrors the flexibility of classical feed-forward networks (adjustable hidden layers and nodes), and decouples qubit requirements from input feature dimension. Compared to prevailing QNN baselines, the CFF-QNN reduces both depth and CNOT count by over 50% while achieving strong performance on standard benchmarks (e.g., 91% accuracy on Wisconsin breast cancer and 85% on credit-card fraud). This contribution is accompanied by an international patent filing (WO2025050205A1). Second, I develop a resource-efficient quantum kernel that enables high-dimensional embeddings with substantially fewer qubits and entanglers, achieving linear scaling of entangling gates in the number of qubits. Empirically, the kernel delivers competitive or superior performance to widely used classical kernels and to popular quantum feature maps (e.g., on the Parkinson's disease dataset), with noisy simulations and small-scale runs on superconducting hardware indicating suitability for near-term devices. This contribution is covered by a companion patent filing (WO2025073041A1). Third, I propose a quantum reservoir computing (QRC) scheme that reuses a fixed quantum feature-map circuit as the reservoir while injecting temporal memory via an explicit feedback loop. The register is recycled across time, so quantum resources remain constant, no quantum parameters are trained, and only a lightweight classical readout is fitted. Experiments on chaotic time series (e.g., Mackey-Glass) show competitive predictive accuracy with strict resource efficiency, and illuminate how feedback delay and entangling structure affect memory and error. Collectively, these results chart a path toward practical QML: coherent architectures and kernels that are trainable, scalable in input dimension, frugal in quantum resources, and viable on noisy intermediate-scale devices—while providing design guidelines for future, larger-scale implementations.
Variational quantum circuits (VQCs) are a leading approach to quantum machine learning on near-term devices, yet it remains unclear which circuit architecture yields the best accuracy-parameter trade-off on classical tabular data. We present a systematic empirical comparison of four VQC families -- multi-layer fully-connected (FC-VQC), residual (ResNet-VQC), hybrid quantum-classical transformer (QT), and fully quantum transformer (FQT) -- across five regression and classification benchmarks. Our key findings are: \textbf{(i)}~FC-VQCs achieve 90-96\% of the R2 of attention-based VQCs while using 40-50\% fewer parameters, and consistently outperform equal-capacity MLPs (mean R2=0.829 vs.\ MLP720's 0.753 on Boston Housing, 3-seed average); \textbf{(ii)}~FC-VQC's Type~4 inter-block connectivity provides partial cross-token mixing that approximates the role of attention -- explicit quantum self-attention yields only marginal gains on most datasets while significantly increasing parameter count; \textbf{(iii)}~expressibility saturates at circuit depth~≈3, explaining why shallow VQCs already cover the Hilbert space effectively; \textbf{(iv)}~LayerNorm on the fully quantum transformer improves classification accuracy, suggesting normalization is important when all operations are quantum; \textbf{(v)}~in our noise study on Boston Housing, FQT degrades gracefully under depolarizing noise while QT collapses. All results are validated across three random seeds. These findings provide practical architectural guidance for deploying VQCs on near-term quantum hardware.
Transformer now underpins modern AI as its core infrastructure. Its defining capability-dynamically focusing on the most relevant information in complex inputs-is bounded above by the self-attention scoring function. Quantum computing, with its superposition, entanglement, and probabilistic outputs, offers a fundamentally distinct computational framework for exploring beyond the design constraints of classical scoring functions. While quantum attention mechanisms have shown initial promise, existing works remain largely confined to redefining feature similarity measures, leaving the systematic use of parameterized quantum circuits (PQCs) as scoring functions largely unexplored; a substantial portion of existing schemes further rely on purely quantum architectures, precluding effective encoding of high-dimensional image inputs in the Noisy Intermediate-Scale Quantum era. We propose the Quantum Parameterized Self-Attention Network (QPSAN), implementing the self-attention scoring function via PQCs with only 5 trainable quantum parameters per layer. QPSAN computes query-key attention scores through quantum state encoding and joint measurement, yielding naturally bounded outputs without the explicit scaling of classical dot-product attention. We further establish a theoretical framework of the mathematical properties of this scoring function, demonstrating its potential to capture complex nonlinear query-key interactions, and quantifying the structural constraints of the encoding layer via effective degrees of freedom analysis. Experiments on four vision datasets show that QPSAN significantly outperforms the Vision Transformer (ViT) baseline, with the quantum representational advantage amplifying as data complexity increases. Ablation studies indicate that the performance gains may stem from the structural inductive bias of the quantum circuit rather than from parameter scale.
Quantum machine learning (QML) for network intrusion detection (NIDS) is routinely reported to reach near-perfect accuracy, yet the most rigorous studies find that well-tuned classical models remain competitive, and that apparent quantum gains may be artefacts of classical dimensionality reduction and implicit regularisation rather than genuine quantum effects. We ask not whether a quantum model can post a high accuracy, but how quantum the advantage really is. We present a unified, reproducible QML-IDS benchmark evaluating hybrid variational quantum circuits and quantum-kernel SVMs against five honestly-tuned classical baselines across four standard NIDS datasets (NSL-KDD, UNSW-NB15, CICIDS2017, NF-ToN-IoT-v2) under one leakage-controlled protocol, with an equal-budget feature view, imbalance- and calibration-aware metrics with significance testing, and a simulated NISQ noise sweep. We introduce a quantum-attribution audit (parameter-matched classical controls, a random-feature kernel, and a regularisation sweep) that quantifies how much of any gain is genuinely attributable to the quantum component. Tuned classical models (Random Forest, XGBoost) match or exceed the quantum models on aggregate detection on every dataset, and the audit attributes this to classical preprocessing and regularisation rather than quantum effects. Two advantages survive false-discovery-rate correction: the quantum-kernel SVM out-ranks its direct classical surrogate (a random-feature kernel) on AUPRC and ROC-AUC, and a small four-qubit hybrid out-detects the best classical baseline at the 1% false-positive operating point on the distribution-shifted NSL-KDD task (p = 0.005, BH q = 0.030). Code, seeds, and splits are released; our contribution stands whether quantum wins, ties, or loses.
Deep sequence models are increasingly combined with quantum computing and quantum-inspired optimization, yet the resulting literature uses inconsistent terminology and reports uneven evidence. This concise review distinguishes quantum-enhanced models, which execute parameterized quantum circuits, from quantum-inspired methods implemented on classical hardware. It organizes recent work by the point at which quantum principles enter the learning pipeline: recurrent gates, attention and feature maps, kernel representations, and training optimizers. Quantum long short-term memory networks and related hybrid architectures demonstrate expressive low-parameter models on small forecasting and classification tasks, while emerging superposition- and tunnelling-inspired optimizers target difficult neural-network loss landscapes. However, most reported gains are based on simulators, limited datasets, and comparisons that do not control computational budgets. The review therefore proposes a compact evaluation framework emphasizing strong classical baselines, wall-clock and energy costs, repeated trials, noise-aware experiments, and transparent definitions of quantum advantage. These practices are necessary to determine whether quantum mechanisms provide practical value for recurrent networks, Transformers, and future large-scale sequence models.