Gate-based quantum computations represent an essential to realize near-term quantum computer architectures. A gate-model quantum neural network (QNN) is a QNN implemented on a gate-model quantum computer, realized via a set of unitaries with associated gate parameters. Here, we define a training optimization procedure for gate-model QNNs. By deriving the environmental attributes of the gate-model quantum network, we prove the constraint-based learning models. We show that the optimal learning procedures are different if side information is available in different directions, and if side information is accessible about the previous running sequences of the gate-model QNN. The results are particularly convenient for gate-model quantum computer implementations.
Gate-based quantum computations represent an essential to realize near-term quantum computer architectures. A gate-model quantum neural network (QNN) is a QNN implemented on a gate-model quantum computer, realized via a set of unitaries with associated gate parameters. Here, we define a training optimization procedure for gate-model QNNs. By deriving the environmental attributes of the gate-model quantum network, we prove the constraint-based learning models. We show that the optimal learning procedures are different if side information is available in different directions, and if side information is accessible about the previous running sequences of the gate-model QNN. The results are particularly convenient for gate-model quantum computer implementations.
Quantum Machine Learning is an emerging sub-field in machine learning where one of the goals is to perform pattern recognition tasks by encoding data into quantum states. This extension from classical to quantum domain has been made possible due to the development of hybrid quantum-classical algorithms that allow a parameterized quantum circuit to be optimized using gradient based algorithms that run on a classical computer. The similarities in training of these hybrid algorithms and classical neural networks has further led to the development of Quantum Neural Networks (QNNs). However, in the current training regime for QNNs, the gradients w.r. t objective function have to be computed on the quantum device. This computation is highly non-scalable and is affected by hardware and sampling noise present in the current generation of quantum hardware. In this paper, we propose a training algorithm that does not rely on gradient information. Specifically, we introduce a novel meta-optimization algorithm that trains a meta-optimizer network to output parameters for the quantum circuit such that the objective function is minimized. We empirically and theoretically show that we achieve a better quality minima in fewer circuit evaluations than existing gradient based algorithms on different datasets.
Quantum Machine Learning is an emerging sub-field in machine learning where one of the goals is to perform pattern recognition tasks by encoding data into quantum states. This extension from classical to quantum domain has been made possible due to the development of hybrid quantum-classical algorithms that allow a parameterized quantum circuit to be optimized using gradient based algorithms that run on a classical computer. The similarities in training of these hybrid algorithms and classical neural networks has further led to the development of Quantum Neural Networks (QNNs). However, in the current training regime for QNNs, the gradients w.r.t objective function have to be computed on the quantum device. This computation is highly non-scalable and is affected by hardware and sampling noise present in the current generation of quantum hardware. In this paper, we propose a training algorithm that does not rely on gradient information. Specifically, we introduce a novel meta-optimization algorithm that trains a \emph{meta-optimizer} network to output parameters for the quantum circuit such that the objective function is minimized. We empirically and theoretically show that we achieve a better quality minima in fewer circuit evaluations than existing gradient based algorithms on different datasets.
This study explores various architectures of Quantum Neural Networks (QNN) that utilize quantum computing to enhance machine learning model performance. The architectures examined include Hybrid Quantum Neural Network (H-QNN), Deep Quantum Neural Network (DQNN), Quantum Convolutional Neural Network (QCNN), and Coherent Feed Forward Quantum Neural Network. Additionally, the EfficientSU2 architecture demonstrated superior performance in accuracy and cost reduction. Optimization techniques such as Adaptive Moment Estimation (ADAM), Analytic Quantum Gradient Descent (AQGD), and Nakanishi-Fujii-Todo (NFT) were integrated to improve training efficiency. The study results show that EfficientSU2 with 10,000 iterations yielded the best results in terms of cost and accuracy across all tested datasets, with accuracy improvements reaching up to 97%. In conclusion, the EfficientSU2 architecture and the applied optimization techniques significantly enhanced the processing of complex data, paving the way for substantial advancements in quantum-based artificial intelligence applications.
Gate-model quantum computers can allow quantum computations in near-term implementations. The stabilization of an optimal quantum state of a quantum computer is a challenge, since it requires stable quantum evolutions via a precise calibration of the unitaries. Here, we propose a method for the stabilization of an optimal quantum state of a quantum computer through an arbitrary number of running sequences. The optimal state of the quantum computer is set to maximize an objective function of an arbitrary problem fed into the quantum computer. We also propose a procedure to classify the stabilized quantum states of the quantum computer into stability classes. The results are convenient for gate-model quantum computations and near-term quantum computers.
Abstract Quantum neural network (QNN), or equivalently, the variational quantum circuits with a gradient-based classical optimizer, has been broadly applied to many experimental proposals for noisy intermediate scale quantum (NISQ) devices. However, the learning capability of QNN remains largely unknown due to the non-convex optimization landscape, the measurement error, and the unavoidable gate noise introduced by NISQ machines. In this study, we theoretically explore the learnability of QNN from the perspective of the trainability and generalization. Particularly, we derive the convergence performance of QNN under the NISQ setting, and identify classes of computationally hard concepts that can be efficiently learned by QNN. Our results demonstrate that large gate noise, few quantum measurements, and deep circuit depth will lead to poor convergence rates of QNN towards the empirical risk minimization. Moreover, we prove that any concept class, which is efficiently learnable by a restricted quantum statistical query (QSQ) learning model, can also be efficiently learned by QNN. Since the restricted QSQ learning model can tackle certain problems such as parity learning with a runtime speedup, our result suggests that QNN established on NISQ devices will retain the quantum advantage. Our work provides the theoretical guidance for developing advanced QNNs and opens up avenues for exploring quantum advantages using NISQ devices.
As the boundaries of quantum computing continue to expand, its intersection with artificial intelligence (AI) is opening new avenues for computational efficiency, model expressiveness, and problem-solving. One such intersection is the emergence of quantum neural networks (QNNs), which synergize the principles of quantum mechanics with classical machine learning frameworks. The practical realization of QNNs, however, is constrained by today’s noisy intermediate-scale quantum (NISQ) devices, characterized by limited qubit counts, decoherence, and noise. This chapter explores how QNNs can be implemented and trained effectively on near-term hardware. We review current quantum computing technologies, examine the architecture of QNNs, discuss hybrid quantum-classical training strategies, and present a practical case study on digit classification. We also review implementation tools such as Qiskit, PennyLane, and TensorFlow Quantum. The chapter concludes with an outlook on future directions and ongoing challenges in realizing scalable, reliable QNNs.