Despite potential quantum supremacy, state-of-the-art quantum neural networks (QNNs) suffer from low inference accuracy. First, the current Noisy Intermediate-Scale Quantum (NISQ) devices with high error rates of 10− 3 to 10− 2 significantly degrade the accuracy of a QNN. Second, although recently proposed Re-Uploading Units (RUUs) introduce some non-linearity into the QNN circuits, the theory behind it is not fully understood. Furthermore, previous RUUs that repeatedly upload original data can only provide marginal accuracy improvements. Third, current QNN circuit ansatz uses fixed two-qubit gates to enforce maximum entanglement capability, making task-specific entanglement tuning impossible, resulting in poor overall performance. In this paper, we propose a Quantum Multilayer Perceptron (QMLP) architecture featured by error-tolerant input embedding, rich nonlinearity, and enhanced variational circuit ansatz with parameterized two-qubit entangling gates. Compared to prior arts, QMLP increases the inference accuracy on the 10-class MNIST dataset by 10% with 2 × fewer quantum gates and 3 × reduced parameters. Our source code is available and can be found in https://github.com/chuchengc/QMLP/.
Despite potential quantum supremacy, state-of-the-art quantum neural networks (QNNs) suffer from low inference accuracy. First, the current Noisy Intermediate-Scale Quantum (NISQ) devices with high error rates of 10− 3 to 10− 2 significantly degrade the accuracy of a QNN. Second, although recently proposed Re-Uploading Units (RUUs) introduce some non-linearity into the QNN circuits, the theory behind it is not fully understood. Furthermore, previous RUUs that repeatedly upload original data can only provide marginal accuracy improvements. Third, current QNN circuit ansatz uses fixed two-qubit gates to enforce maximum entanglement capability, making task-specific entanglement tuning impossible, resulting in poor overall performance. In this paper, we propose a Quantum Multilayer Perceptron (QMLP) architecture featured by error-tolerant input embedding, rich nonlinearity, and enhanced variational circuit ansatz with parameterized two-qubit entangling gates. Compared to prior arts, QMLP increases the inference accuracy on the 10-class MNIST dataset by 10% with 2 × fewer quantum gates and 3 × reduced parameters. Our source code is available and can be found in https://github.com/chuchengc/QMLP/.
With the limitations of current noisy intermediate scale quantum (NISQ) devices, there is a need for hybrid quantum-classical learning models to operate more efficiently within existing hardware constraints. The design of cost-effective hybrid quantum-classical learning systems is therefore imperative for various applications, including biosignal processing in the healthcare sector. This motivates the investigation into the reduction of computational complexity of a hybrid quantumclassical neural network. We propose a new hybrid model combining a quantum neural network (QNN) with a binary neural network (BNN), known as quBNN, with the aim to reduce model complexity. For benchmarking, we consider a classical multilayer perceptron (MLP) and a standard nonbinarised version of quBNN that combines a QNN with an MLP, named as quilp. We evaluated all models on a multi-class dataset containing multimodal biosignals. We find that quMLP can outperform the classical MLP with minimal additional complexity, while quBNN maintains performance comparable with the classical MLP, with reduced computational complexity. We apply pruning and quantisation techniques to the QNN within the proposed quBNN model, aiming to further reduce its complexity. This compression yields substantial reductions in parameter and quantum gate count when compiled for quantum hardware, albeit with performance degradation.
Quantum machine learning (QML) is promising for potential speedups and improvements in conventional machine learning (ML) tasks (e.g., classification/regression). The search for ideal QML models is an active research field. This includes identification of efficient classical-to-quantum data encoding scheme, construction of parametric quantum circuits (PQC) with optimal expressivity and entanglement capability, and efficient output decoding scheme to minimize the required number of measurements, to name a few. However, most of the empirical/numerical studies lack a clear path towards scalability. Any potential benefit observed in a simulated environment may diminish in practical applications due to the limitations of noisy quantum hardware (e.g., under decoherence, gate-errors, and crosstalk). We present a scalable quantum-classical hybrid deep neural network (DeepQMLP) architecture inspired by classical deep neural network architectures. In DeepQMLP, stacked shallow Quantum Neural Network (QNN) models mimic the hidden layers of a classical feed-forward multi-layer perceptron network. Each QNN layer produces a new and potentially rich representation of the input data for the next layer. This new representation can be tuned by the parameters of the circuit. Shallow QNN models experience less decoherence, gate errors, etc. which make them (and the network) more resilient to quantum noise. We present numerical studies on a variety of classification problems to show the trainability of DeepQMLP. We also show that DeepQMLP performs reasonably well on unseen data and exhibits greater resilience to noise over QNN models that use a deep quantum circuit. DeepQMLP provided up to 25.3% lower loss and 7.92% higher accuracy during inference under noise than QMLP.
Quantum Machine Learning (QML) has recently emerged as a highly promising research frontier. Within this domain, Quantum Neural Networks (QNNs),characterized by Variational Quantum Circuits (VQCs) at their core and featuring layers of quantum gates optimized by classical algorithms, have garnered significant attention. However, a rigorous and exhaustive evaluation of their practical performance remains largely incomplete. In this study, we conduct a comprehensive comparative analysis of three prominent hybrid classical-quantum architectures: Quantum Convolutional Neural Networks (QCNN), Quantum Recurrent Neural Networks (QRNN), and Quantum Vision Transformers (QViT), focusing on the critical dimensions of generalization, accuracy, and robustness. Our findings provide novel insights that address previous evaluative gaps. Notably, while these models exhibit exceptional performance on low-feature datasets such as MNIST, their learning efficacy degrades significantly when transitioned to high-feature datasets. Furthermore, convolutional-based models like QCNN appear less effective on high-dimensional data than other machine learning architectures. Additionally, while all models are susceptible to adversarial noise, traditional architectures, such as recurrent and convolutional networks, demonstrate superior resilience. Conversely, in the presence of quantum noise, the transformer-based architecture proves its strength by maintaining high robustness against measurement noise, channel noise, and finite-shot effects, whereas other architectures suffer marked performance declines. These results provide a granular perspective on the current state of the field and underscore the critical importance of tailoring model selection to the constraints of contemporary Noisy Intermediate-Scale Quantum (NISQ) environments.
Pain pathways and interpatient variability represent an ongoing challenge for nociception monitoring. Inter- and intrapatient variability require large patient data for training conventional nociception predictive models. In this paper, we propose a quantum multilayer perceptron (QMLP) model for nociception prediction utilizing quantum features such as entanglement which enables the capturing of complex parameter dependencies using less data, by representing intralayer connections between parameters. Our QMLP architecture encodes input physiological parameters into quantum states which are processed through entangled quantum circuits, and optimized using parameter shift rule for gradient estimation. Our nociception prediction model is trained and evaluated on surgical data collected from two hospitals, with features extracted from electrocardiogram, photoplethysmography, and electroencephalogram. Through systematic comparative analysis across multiple datasets using two sampling approaches (patient-wise and downsampling), we demonstrate that our QMLP model consistently outperforms different classical baselines including deep learning models, tree-based ensembles, and linear models across all evaluation metrics. Clinical evaluation on different populations of patients confirms the QMLP model’s superior ability to predict nociceptive changes during surgical events including Intubation, Incision, and Extubation. Expressivity analysis reveals that QMLP models achieve approximately twice the local effective dimension of classical baselines with identical parameter counts. Entanglement topology analysis demonstrates that circular configuration consistently achieves lower training loss compared to linear, pairwise, and non-entangled architectures, with quantum advantage driven by entanglement structure independent of data quantity. Our findings suggest quantum neural networks might offer advantages for nociception monitoring in anesthesia applications, particularly in data-limited scenarios where complex interrelated parameters influence clinical outcomes. The code used in this research can be accessed from:https://github.com/oyanoth/qmlp-nociception.
Abstract Quantum machine learning, focusing on quantum neural networks (QNNs), remains a vastly uncharted field of study. Current QNN models primarily employ variational circuits on an ansatz or a quantum feature map, often requiring multiple entanglement layers. This methodology not only increases the computational cost of the circuit beyond what is practical on near-term quantum devices but also misleadingly labels these models as neural networks, given their divergence from the structure of a typical feed-forward neural network (FFNN). Moreover, the circuit depth and qubit needs of these models scale poorly with the number of data features, resulting in an efficiency challenge for real-world machine learning tasks. We introduce a bona fide QNN model, which seamlessly aligns with the versatility of a traditional FFNN in terms of its adaptable intermediate layers and nodes, absent from intermediate measurements such that our entire model is coherent. This model stands out with its reduced circuit depth and number of requisite CNOT gates, achieving a more than 50% reduction in both compared to prevailing QNN models. Furthermore, the qubit count in our model remains unaffected by the data’s feature quantity. We test our proposed model on various benchmarking datasets such as the breast cancer diagnostic (Wisconsin) and credit card fraud detection datasets. Our model achieved an accuracy of 91% on the breast cancer dataset and 85% on the credit card fraud detection dataset, outperforming existing QNN methods by 5–10% while requiring approximately 50% fewer quantum resources. These results showcase the advantageous efficacy of our approach, paving the way for the application of quantum neural networks to relevant real-world machine learning problems.
Quantum Neural Networks (QNNs) based on parameterized quantum circuits (PQCs) are gaining significant research attention due to their potential to achieve quantum advantages on Near-Term Noisy Intermediate-Scale Quantum (NISQ) computers. However, executing QNNs on NISQ devices is challenging due to quantum noise. To address this, we propose a noise-resilient QNN (NR-QNN) that leverages the unique characteristics of PQCs to perform noise-aware optimizations during the inference stage of QNNs. Specifically, NR-QNN employs two optimization techniques to mitigate the impact of noise on QNNs: quantum pruning and sensitivity-aware qubit mapping. The first technique is quantum pruning which identifies gates with small angle of rotations and removes them to simplify circuit of QNNs. The second optimization technique is sensitivity-aware qubit mapping which maps more important logical qubits to more reliable physical qubits. This technique is based on the observation that there can be variation in the sensitivity of an output to input qubits in a QNN. NR-QNN exploits this variability and guides qubit allocation to use reliable physical qubits for sensitive logical qubits. Our evaluation on a real quantum computer demonstrates that NR-QNN enhances the robustness of QNNs, enabling them to operate effectively on NISQ devices.