Quantum Convolutional Neural Networks (QCNNs) have emerged as one of the most promising architectures in Quantum Machine Learning (QML), enabling hierarchical quantum feature extraction and offering potential advantages over classical CNNs in expressivity and scalability. This study presents a Systematic Literature Review (SLR) on QCNN development from 2019 to 2025, covering theoretical foundations, model architectures, noise resilience, benchmark performance, and applications in materials informatics, chemistry, image recognition, quantum phase classification, and cybersecurity. The SLR followed PRISMA guidelines, screening 214 publications and selecting 47 primary studies. The review finds that QCNNs consistently outperform classical baselines in small-data and high-dimensional regimes due to quantum feature maps and entanglement-driven locality. Significant limitations include noise sensitivity, limited qubit availability, and a lack of standardized datasets for benchmarking. The novelty of this work lies in providing the first comprehensive synthesis of QCNN research across theory, simulations, and real-hardware deployment, offering a roadmap for research gaps and future directions. The findings confirm that QCNNs are strong candidates for NISQ-era applications, especially in physics-informed learning.

Corrosion inhibition efficiency (IE%) prediction plays a central role in the computational discovery of high-performance organic inhibitors. Classical machine learning has shown promising results; however, its performance often deteriorates when learning non-linear interactions between quantum chemical descriptors. Meanwhile, quantum machine learning (QML) provides enhanced expressivity through quantum feature mapping but remains limited by NISQ-era hardware. In this study, we propose a Hybrid Quantum Neural Network (HQNN) integrating classical dense layers with variational quantum circuits (VQC) to predict the inhibition efficiency of organic corrosion inhibitors. Using a curated dataset of 660 molecules with DFT descriptors, the HQNN achieves an RMSE of 3.41 and R² of 0.958, outperforming classical regressors and pure VQC. The results demonstrate that hybrid quantum models offer a balanced trade-off between quantum advantage and practical feasibility in materials informatics.

Accurately predicting the lifetime of lithium-ion batteries during early charge–discharge cycles remains a significant challenge due to the nonlinear and weakly expressed degradation dynamics in the initial stages of operation. Classical machine learning (ML) models—although effective in pattern recognition—often face limitations in modeling complex correlations within small, high-dimensional datasets. To address these challenges, this study proposes a Hybrid Quantum–Classical Machine Learning (HQML) framework that integrates a Variational Quantum Circuit (VQC) as a quantum feature encoder with a Gradient Boosting Regressor (GBR) as the classical learner. The proposed approach is implemented using the Qiskit Aer simulator on the MIT Battery Degradation Dataset (124 cells, 42 engineered features). By encoding multi-source degradation descriptors (voltage, capacity, temperature, internal resistance) into Hilbert space via amplitude and angle encoding, the HQML model captures intricate nonlinear feature interactions that are inaccessible to conventional kernels. Experimental results demonstrate that the hybrid model achieves an RMSE of 93 cycles and an R² of 0.94, outperforming the best classical baseline (SVM + Wrapper selection, RMSE = 115, R² = 0.90). Furthermore, quantum observables analysis reveals interpretable correlations between entanglement strengths and physical degradation indicators. These results highlight the potential of quantum machine learning as a powerful paradigm for high-fidelity battery prognostics in the early-life regime.

Variational Quantum Circuits (VQCs) have emerged as a cornerstone of hybrid quantum–classical algorithms designed to harness the computational potential of near-term quantum devices. By combining parameterized quantum gates with classical optimization, VQCs provide a flexible framework for tackling machine learning, chemistry, and optimization problems intractable for classical methods. This review comprehensively overviews VQC design principles, ansatz structures, optimization strategies, and real-world applications. Furthermore, we discuss fundamental challenges such as barren plateaus, the expressibility–trainability trade-off, and current noisy intermediate-scale quantum (NISQ) hardware limitations. Finally, we highlight emerging directions that could enable scalable, noise-resilient, and physically interpretable variational quantum models for future quantum computing applications

Quantum Neural Networks (QNNs) represent a novel computational paradigm that merges the principles of quantum computing with the architecture of artificial neural networks. Through the quantum phenomena of superposition, entanglement, and interference, QNNs enable parallel computation in high-dimensional Hilbert spaces, offering the potential to surpass the representational limits of classical models. This review provides a comprehensive overview of the theoretical foundations and architectures of QNNs, including Quantum Perceptrons, Variational Quantum Circuits (VQCs), Quantum Convolutional Neural Networks (QCNNs), and Quantum Recurrent Neural Networks (QRNNs). Furthermore, it discusses hybrid quantum–classical training mechanisms and key challenges such as barren plateaus, decoherence, and sampling complexity. The review also highlights recent applications of QNNs in medical diagnostics, materials science, and financial forecasting, demonstrating their potential to accelerate computation and improve predictive accuracy. Finally, future research directions are discussed in relation to computational efficiency, model interpretability, and integration with next-generation quantum hardware.

The convergence of quantum computing and artificial intelligence has introduced a new paradigm in computational science known as Quantum Artificial Intelligence (QAI). By leveraging quantum mechanical principles such as superposition, entanglement, and quantum parallelism, QAI aims to overcome the limitations of classical machine learning, particularly in handling high-dimensional data, complex optimization, and scalability issues. This paper presents a comprehensive review of foundational concepts in both classical machine learning and quantum computing, followed by an in-depth discussion of emerging quantum algorithms tailored for AI applications, such as quantum neural networks, quantum support vector machines, and variational quantum classifiers. We explore the practical implications of these approaches across key sectors, including healthcare, finance, cybersecurity, and logistics. Furthermore, we identify critical challenges related to hardware limitations, algorithmic stability, data encoding, and ethical considerations. Finally, we outline research directions necessary to advance the field, highlighting the transformative potential of QAI in shaping the next generation of intelligent technologies

We introduce the Tree Tensor Network-enhanced Quantum-Classical Neural Network (TTN-QNet), a hybrid architecture that leverages the hierarchical structure of Tree Tensor Networks for efficient parameter representation and Variational Quantum Circuits (VQC) for expressive modeling. Unlike Tensor Ring Networks, TTNs reduce parameter redundancy through a tree-based topology, enabling scalable and interpretable computation. The proposed TTN-QNet is evaluated on the Iris, MNIST, and CIFAR-10 datasets, achieving classification accuracies of 93.2%, 85.24%, and 81.67%, respectively, on binary classification tasks. TTN-QNet demonstrates rapid convergence and robustness against barren plateaus, offering a promising direction for deep quantum learning.

Barren plateaus (BP) remain a core challenge in training quantum neural networks (QNN), where gradient vanishing hinders convergence. This paper proposes a layerwise quantum training (LQT) strategy, which trains parameterized quantum circuits (PQC) incrementally by optimizing each layer separately. Our approach avoids deep circuit initialization by gradually constructing the QNN. Experimental results demonstrate that LQT mitigates the onset of barren plateaus and enhances convergence rates compared to conventional and residual-based QNN, rendering it a scalable alternative for Noisy Intermediate-Scale Quantum (NISQ)-era quantum devices.

This study evaluates gate-based quantum machine learning (QML) models, including the Variational Quantum Classifier (VQC) and Quantum k-Nearest Neighbors (QkNN), on the QM9 quantum chemistry dataset for binary classification of molecular electronic properties. Using IBM Qiskit, both models were tested on simulators and real quantum hardware. Classical models (LightGBM, SVM, MLP) served as benchmarks. Results show classical models outperform quantum ones, with LightGBM achieving the highest AUC-ROC (0.901). However, VQC on simulators achieved a competitive AUC of 0.781, and real hardware still yielded performance above that of chance. Despite hardware constraints, quantum models demonstrated learning capability. The findings support hybrid quantum-classical systems as a promising near-term approach while quantum hardware continues to evolve

This study investigates the performance of classical, quantum, and hybrid classical-quantum stacking models in predicting Corrosion Inhibition Efficiency (IE%) using 14 QSAR descriptors. The hybrid model combines a Gradient Boosting Regressor (GBR) and a Quantum Support Vector Regressor (QSVR) through a meta-learner (Ridge Regression). Results show a significant improvement over traditional models. The hybrid stacking model achieved an R² of 0.834, an MSE of 8.123, an MAE of 2.371, and an RMSE of 2.850, outperforming both individual classical and quantum models. These results confirm the strength of hybrid models in capturing both complex nonlinear and quantum-interaction patterns in QSAR-based molecular prediction.