Aug 2026· International Journal of Innovative Research in Engineering· 0 citations
TL;DR
The results indicate the viability of direct multi-class classification using sequential nonlinear feature encoding and parameterized quantum processing in the studied statevector setting, without asserting the existence of any general quantum computational advantage.
Abstract
Most of the used parameterized quantum circuit classifiers are created for binary problems and can later be generalized to multi-class problems via one-vs-all decomposition, which leads to a bigger number of models and higher costs of inference. In this paper, authors present Adaptive Non-Linear Quantum Neural Network (ANQNN) that performs direct classification of images into ten classes according to their eight-qubit statevector. Each 16×16 image is transformed into a vector of 256 features and divided into 32 sequential chunks of 8 features each that are processed sequentially. Prior to an encoding procedure, a special adaptive nonlinear transformation is applied to improve a simple linear term with trainable cubic and sinusoidal terms. Each chunk is encoded using the RY rotations and processed by means of subsequent chunk-specific RZ−RY−RZ rotations followed by controlled ring entanglement. During training, the adaptive angle of mixing influences the state of quantum mixture and at the end, 8 Pauli-Z expectation values are mapped to ten class logits via linear readout. The tests on MNIST and Fashion-MNIST datasets yielded 90.85% and 80.12% of accuracies respectively with mean one-vs-rest AUC values equaling to 0.9931 and 0.9748 respectively.The results indicate the viability of direct multi-class classification using sequential nonlinear feature encoding and parameterized quantum processing in the studied statevector setting, without asserting the existence of any general quantum computational advantage.
Quantum Machine Learning (QML) combines quantum computing principles and traditional machine learning principles to provide new ways to solve difficult classification problems through the use of quantum technology. The goal of this paper is to implement a Quantum Kernel Support Vector Machine (QKSVM) using PennyLane and evaluate it against a standard image classification dataset, Fashion-MNIST. The Fashion-MNIST images are represented as 28x28 grayscale pixel arrays; they are normalized using a min-max normalizer with output values between zero and one. The 28x28 arrays are then dimensionally reduced to a size of four principal components (approximately 85% cumulative explained variance), and the QKSVM will utilize a quantum circuit limited to four qubits which is consistent with today's Noisy, Intermediate-Scale Quantum (NISQ) capabilities for performing simulations. Each input feature is represented as a qubit via an RY rotation and the qubits are then entangled using a CNOT circuit to generate the quantum kernel matrix, which is computed as the pairwise fidelity of each input image's state, which is subsequently used by a classical SVM classifier implementing a one-versus-all classification method. The QKSVM achieved approximately 40% accuracy and a macro-F1 score of 0.37 on a 100 sample stratified subset of the Fashion-MNIST test dataset, compared with 60% and 91.2%, respectively, using a classical Radial Basis Function Support Vector Machine (RBF-SVM) classifier with the same four principal components of input features and a Convolutional Neural Network (CNN) with full input images. With a primary bottleneck of qubit count, circuit depth, and shot noise, this work serves as a fully documented and reproducible baseline for future research on quantifying the performance of hybrid classical and quantum image classifiers across standardized image dataset benchmarks.
M. Devi, S.Sravanthi, V. Chaithanya et al.· 2026 7th International Confe...· 0 citations
Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory constraints. In the Noisy Intermediate-Scale Quantum (NISQ) era, although quantum neural networks offer advantages in feature mapping, hardware limitations restrict circuit width. Furthermore, traditional quantum classifiers are constrained by the number of orthogonal basis states, limiting their capacity to accommodate a continually growing number of categories. Thus, we introduce a novel quantum incremental learning framework based on trainable mixed-state prototypes. Its original design incorporates new classes by adding class prototypes rather than increasing the circuit width of the shared quantum backbone. The use of mixed-state prototypes is another key contribution, since they have representation capabilities to represent information than a single pure-state prototype. And the decomposable mixed-state calculation provides lower production costs and a convenient Hilbert-Schmidt (HS) distance metric for classification. Simulation results show that our model achieves high-dimensional feature concentration using a minimal number of qubits, while demonstrating lower computational complexity and robust representation in incremental learning tasks compared with classical baselines.
Yu Wu, Qian-Li Zhou, Xin-Yang Deng et al.· 0 citations
A controlled optimizer-aware evaluation framework that integrates a fixed ZZFeatureMap–TwoLocal VQC architecture with callback-based convergence diagnostics to systematically analyse optimizer behaviour under identical experimental conditions is presented.
R. D, R. R., Sridevi S et al.· International Research Journ...· 0 citations
Quantum convolution offers a natural inductive bias for extracting local structure from high-dimensional data, yet its practical reach is constrained by direct feature-wise encoding, which ties broader receptive fields to wider quantum registers. This raises a central question: can local quantum representations retain their predictive content when receptive-field growth is redirected from circuit width to sequential processing on a compact register? Generalized Quantum Neural Modules address this question through incremental data upload, partitioning each receptive field into ordered batches, preserving a single evolving quantum state across successive encode–entangle stages, and reusing shared trainable transformations as the local window moves across the input. State-vector experiments on controlled three- and four-dimensional motif tensors, MNIST images, and selected UCF101 action videos show that moderate serialization substantially narrows the active register while preserving the predictive behaviour of direct encoding; more aggressive partitioning, by contrast, reveals a progressive trade-off between sequential depth and within-batch feature interaction, with mixed CRZ–CRX entanglement providing the most effective fixed-width configuration. Together, these results delineate a practical operating regime for high-dimensional local quantum learning and show that receptive-field scaling can be managed through a coordinated choice of upload granularity, entangling structure, information retention, and execution depth.
Wen-Bin Yu, Yan-Feng Fan, You-Le Wang et al.· Machine Learning: Science an...· 0 citations
Neural network quantum states (NQS) for representing spin-$\frac{1}{2}$ systems are typically built from Multi-Layer Perceptrons (MLPs) with binary visible variables, in which the input spins are first combined through linear affine maps before more expressive nonlinear transformations are applied. The standard way for representing multi-categorical systems, namely spin-1 and spin-2, or the q-state quantum Potts systems with more than two local degrees of freedom, is a unary or one-hot encoded MLP architecture. Following a few similar studies, I observe that while the one-hot construction is the mathematically faithful encoding for systems with more than two local states such as spin-$S$ models with $S>1/2$ or $q$-state Potts models, its parameter count grows with the number of local states, and the resulting optimization landscape can hinder convergence. I find numerically that allowing $\log \Psi$ to be a nonlinear function of the raw multi-valued spin variable is a natural categorical generalization: it preserves the labelling freedom of the local basis and reproduces the one-hot model with strictly fewer parameters, often with improved trainability. I first benchmark this idea on shallow Restricted Boltzmann Machines (RBMs), equipping them with several distinct nonlinear connections, for spin-1, 2, and 3 Heisenberg chains. I then turn to Kolmogorov-Arnold Networks (KANs), where each edge carries a learnable univariate nonlinearity, and show that they provide a strictly more expressive realization of the same principle. Finally, I demonstrate that this framework captures the critical behaviour of the quantum Potts Hamiltonian, recovering its phase transition.
Quantum convolutional neural networks (QCNNs) typically consist of quantum encoding, convolution, and pooling layers. However, existing QCNNs for image classification still face two major limitations. Most encoding layers rely on single-parameter angle encoding, which limits their ability to represent complex image features. Many circuit architectures are relatively deep, increasing cir cuit complexity and noise accumulation and thus hindering implementation on noisy intermediate-scale quantum devices. To address these issues, this paper proposes a low-depth three-parameter encoding quantum convolutional neural network (LTP-QCNN) for image classification. The model employs a three parameter angle encoding layer that maps compressed image features onto the rotation angles of single-qubit gates. A first low-depth quantum convolutional layer is employed to extract local features, followed by a quantum pooling layer for quantum-state dimensionality reduction and information fusion. The pooled quantum states are then processed by a second quantum convolutional layer to extract discriminative features. Finally, the measured quantum feature vector is input into a classical classification layer to produce the final prediction. Simulation experiments were conducted on the Fashion-MNIST, MNIST, and KMNIST benchmark datasets. On Fashion-MNIST, LTP-QCNN achieved an accuracy of 99.85% on binary classification, while the accuracies for five-class and six class tasks reached 90.98% and 89.48%, respectively. The results demonstrate that LTP-QCNN achieves effective and stable image classification under limited quantum resources.
Jing Wang, Yong Zhang, Min Zhao· Indonesian Journal of Electr...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
