We study parameterized quantum circuits (PQCs) integrated as residual sidecar modules within a ResNet-50 backbone for 31-class neural population decoding---imagined handwriting classification from multi-neuron spike rasters. Under strictly controlled conditions (fixed data splits, seeds, and optimizer), we compare four model variants: baseline, quantum sidecar with frozen input projection, quantum sidecar with backbone-gradient-trained projection, and a measurement-guided variant that aligns angle encodings with circuit measurement outcomes. The backbone-gradient variant improves accuracy in 3/4 seeds (+0.19% mean, 95% CI [-1.10%, +1.48%]) and consistently reduces Linear CKA similarity to baseline features ($Δ=-0.025$, 4/4 seeds), indicating genuine structural reorganization of representations. A nine-variant ablation identifies simple shallow architectures as the most effective and reproducible configuration. Measurement-guided training consistently improves representation geometry without reducing accuracy. All results use noiseless statevector simulation on 4 qubits, a regime chosen to reflect the practical constraints of current near-term superconducting hardware; no quantum computational advantage over classical methods is claimed.
Comments
Accepted at the 5th International Workshop on Human Brain and Artificial Intelligence (HBAI 2026), IJCAI-ECAI 2026
We study parameterized quantum circuits (PQCs) integrated as residual sidecar modules within a ResNet-50 backbone for 31-class neural population decoding---imagined handwriting classification from multi-neuron spike rasters. Under strictly controlled conditions (fixed data splits, seeds, and optimizer), we compare four model variants: baseline, quantum sidecar with frozen input projection, quantum sidecar with backbone-gradient-trained projection, and a measurement-guided variant that aligns angle encodings with circuit measurement outcomes. The backbone-gradient variant improves accuracy in 3/4 seeds (+0.19% mean, 95% CI [-1.10%, +1.48%]) and consistently reduces Linear CKA similarity to baseline features (Δ=−0.025, 4/4 seeds), indicating genuine structural reorganization of representations. A nine-variant ablation identifies simple shallow architectures as the most effective and reproducible configuration. Measurement-guided training consistently improves representation geometry without reducing accuracy. All results use noiseless statevector simulation on 4 qubits, a regime chosen to reflect the practical constraints of current near-term superconducting hardware; no quantum computational advantage over classical methods is claimed.
Given the recent prominence of Noisy Intermediate Scale Quantum (NISQ) devices, hybrid quantum-classical neural networks have recently drawn a lot of excitement as a potential solution to improving learning efficiency. Our current paper describes a Hybrid Quantum-Classical Convolutional Neural Network (HQCNN) which is defined as a pretrained backbone of ResNet-18 and a small quantum-enhanced feature-transformation layer of Qiskit. The convolutional high-dimensional features are reduced to the classical eight-dimensional one, which in turn is encoded into a four-qubit parameterized quantum circuit. The resultant quantum expectation values are combined with the compressed features to come up with a hybridized representation of twelve dimensions, used to classify multi-class dataset. Experimental analysis of CIFAR10 data has shown that the suggested HQCNN achieves a test accuracy of 94.74% and improves class-wise precision, recall, and F1-scores than a number of existing hybrid models while using a significantly smaller number of latent features. More investigation into the quantum module indicates that it is predictable about scalability to batch, resistant to perturbations in features, and efficiently performed by evaluating circuit vectors. These results indicate that compact and expressive representations of images that can be helpful in the NISQ era can be acquired using hybrid architectures, thus providing a practical way to forward the benefits of quantum to modern deep-learning pipelines.
The proposed work developed a robust hybrid quantum neural network model (HQNN) to mitigate the model overfitting problem for MRI brain tumour diagnosis. As quantum computing is the future of computation, the proposed work analyzed the impact of quantum layers on HQNN architectures and quantum advantages in improving model generalisation through an ablation study. We designed a single-layered shallow 10-Qubit parameterised quantum circuit (PQC) to reduce the model’s overfitting. Fifteen HQNN models were designed, incorporating a diverse set of quantum gate arrangements to explore their effects on model performance. Through ablation experiments, the proposed work utilised the substantial impact of single-layered shallow PQC with RX rotation, H-Gate superposition, and CZ entanglement in improving model expressivity and more stable performance on validation data, and enhanced the model's robustness. The proposed PQC compensates for the reduced regularisation effect caused by turning off 10% of neuron activations at each training step in the HQNN model. It improved the validation accuracy of the model by 4.73%, indicating better generalisation than classical FCNN models. The proposed work used brain tumour classification datasets from Kaggle and figshare repositories. We compared our HQNN model with state-of-the-art (SOTA) methods on standard MRI brain tumour datasets. The proposed HQNN model outperformed the SOTA methods with 98.17% test accuracy in binary classification and 96.97% test accuracy in multi-class classification.
Quantum Neural Networks (QNNs) represent a compelling convergence of quantum mechanics and machine learning, yet their practical deployment remains constrained by noise, limited qubit counts, and the cost of full quantum execution. Hybrid quantum-classical (HQC) training offers a pragmatic path forward: parameterized quantum circuits (PQCs) process information in exponentially large Hilbert spaces while classical optimizers update parameters via gradient methods accessible on today's hardware. We present a modular HQC training framework, formalising the parameter-shift rule for hardware-compatible gradient estimation, characterising the barren-plateau phenomenon through a variance-decay analysis, and introducing noise-aware training strategies for NISQ devices. Empirical results from state-vector and shot-based simulation confirm measurable quantum advantage on quantum-structured tasks, with the phase classification benchmark improving +12.1% over a classical MLP baseline. The accompanying open-source library provides a clean abstraction between quantum simulation and classical optimisation, serving as a foundation for near-term quantum machine learning research.
Quantum-inspired optimization algorithms have emerged as a compelling alternative to fully quantum approaches, leveraging classical hardware to simulate key quantum features—such as superposition, entanglement analogs, and parameterized variational circuits—to solve high-dimensional, nonconvex optimization problems more efficiently than traditional heuristics. This manuscript presents Quantum-Inspired Edge AI Optimization for Neural Prosthetics (QEAI-O-NP), a comprehensive framework that integrates a Variational Quantum-Inspired Optimizer (VQIO) with a Spiking Neural Network (SNN) decoder, both tailored for on-device execution on resource-constrained edge platforms. Combining a hybrid quantum-classical metaheuristic surrogate of the Quantum Approximate Optimization Algorithm (QAOA) with low-power neuromorphic inference, QEAI-O-NP addresses challenges of adaptive weight tuning, latency, and energy efficiency inherent to real-time electromyographic (EMG) signal decoding for prosthetic control. The framework preprocesses multi-channel EMG via bandpass filtering and windowing, encodes features into spike trains, and performs classification through a three-layer LIF-based SNN. Periodically, the VQIO formulates the current loss landscape as a cost Hamiltonian and executes two-layer QAOA-inspired tensor-network simulations to extract gradient estimates for synaptic weight updates. Deployed on an NVIDIA Jetson Xavier NX, QEAI-O-NP achieves a 15% absolute gain in decoding accuracy (from 80.2% to 95.2%), reduces inference latency by 30% (from 45.8 ms to 32.1 ms), and cuts energy consumption per inference by 25% (from 193 mJ to 145 mJ) compared to state-of-the-art edge AI baselines. An ablation study explores the trade-offs of QAOA depth and update frequency, guiding practical parameter selection.
Abstract Quantum machine learning (QML) has recently been explored as a means of augmenting classical convolutional neural networks (CNNs) for medical image analysis, yet most existing hybrid architectures insert a single quantum component either at the input or the output of an otherwise classical pipeline, and few works empirically isolate which placement is actually responsible for performance change. This paper proposes QCQ-CNN, a Quantum-Classical-Quantum hybrid framework for brain tumor magnetic resonance imaging (MRI) classification in which a quantum convolutional (“quanvolutional”) layer performs early-stage feature extraction, a classical CNN backbone performs hierarchical representation learning, and a variational quantum circuit (VQC) performs final classification, so that quantum processing brackets the classical backbone at both ends. Using a real, held-out four-class brain tumor MRI dataset (glioma, meningioma, pituitary tumor, and no tumor), we implement and train four architectural variants under matched conditions — (A) a fully classical CNN baseline, (B) a quantum-convolution-plus-classical-CNN variant, (C) a classical-CNN-plus-quantum-head variant, and (D) the full proposed QCQ-CNN — and report actual experimental accuracy, precision, recall, and F1-score on a common test set, together with training curves, confusion matrices, and qualitative visualizations of the learned quantum feature maps. Our small-scale experiments show that quantum convolutional preprocessing alone improves macro-F1 over the classical baseline (0.204 to 0.382), while replacing the classical classification head with a variational quantum circuit degrades performance in both the quantum-head-only and the full QCQ-CNN configurations. We discuss this finding in the context of variational quantum circuit trainability at low qubit counts and limited data, and argue that our staged ablation methodology — rather than a single best-accuracy claim — constitutes the paper's principal novelty: a reusable protocol for empirically localizing where, in a CNN pipeline, quantum layers help versus hurt. We conclude with concrete design recommendations and directions for scaling QCQ-style frameworks. Keywords: Quantum Machine Learning, Hybrid Quantum-Classical Neural Networks, Quanvolutional Neural Network, Variational Quantum Circuit, Convolutional Neural Network, Brain Tumor Classification, Medical Image Processing
Quantum neural networks (QNNs) have recently attracted remarkable attention as a potential alternative to classical and deep neural network (NN) models particularly under constraints imposed by noisy intermediate-scale quantum (NISQ) devices, which support only shallow circuits with few quantum bits (qubits) and limited variational depth. However, applying QNNs to natural language processing (NLP) remains challenging because text representations are typically high-dimensional, while NISQ classifiers can only encode a small number of features at a time, requiring classical compression to enable stable training and flexible circuit configuration. In addition, many existing studies integrate QNNs into rich-text representation pipelines, where the quantum circuit is often implemented as a variational quantum circuit (VQC). Here, the VQC acts as an additional component within a larger model, and it remains unclear how the quantum component improves the classification task. Therefore, in this work, we propose a fully reproducible and compact QNN pipeline that provides a controlled setting for studying the contribution of the VQC to text classification. The model is trained end-to-end with a lightweight classical compression layer, and the overall study is supported by systematic ablation analyses of the compression layer, the classifier heads under a shared frozen low-dimensional representation, and quantum circuit structure. Our model uses the term frequency-inverse document frequency (TF-IDF) features with linear compression followed by a shallow four-qubit, two-layer VQC, implemented in PyTorch and PennyLane for end-to-end training. It is evaluated on five benchmark text classification datasets against classical baselines, including logistic regression and multilayer perceptron (MLP) models. Experimental results show that the proposed QNN achieves a competitive performance across all evaluated datasets, yielding the best results on three of the five benchmark datasets.