A Review of Quantum Neural Networks

S. K. Jeswal, Snehashish Chakraverty

Han Qi, Lei Wang, Hongsheng Zhu +2 more

Muhamad Akrom

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.

憲明 幸田

Teodor Cervinski, Cristian Toma, Claudiu Brândaș +1 more

Quantum computing opens new frontiers for modeling intelligence at the physical level. This paper investigates Quantum Neural Networks (QNNs) not just as tools for classification but analyzing in terms of performance and carbon footprint as an alternative to the classic implementations. Starting with reviewing a simple algorithm solved with standard Neural Network (NN) with different processing approaches (CPU/GPU) and then design a QNN circuit. After running on different platforms, we can do analysis and benchmarking regarding the performance. The paper analyzes the parallels between quantum gates and transistor logic, proposing hybrid designs that transpose neuron-inspired behaviors into various circuits. Through simulations and literature review, the authors examine the feasibility of such quantum-neuromorphic architectures and discuss them. This work aims to bridge neuroscience, electronics, and quantum computing, highlighting a novel pathway for scalable, high performance quantum AI.

Do Ngoc Diep