Quantum neural networks (QNN) have been proposed as a promising architecture for quantum machine learning. There exist a number of different quantum circuit designs being branded as QNNs, however no clear candidate has presented itself as more suitable than the others. Rather, the search for a ``quantum perceptron" -- the fundamental building block of a QNN -- is still underway. One candidate is quantum perceptrons designed to emulate the nonlinear activation functions of classical perceptrons. Such sigmoid quantum perceptrons (SQPs) inherit the universal approximation property that guarantees that classical neural networks can approximate any function. However, this does not guarantee that QNNs built from SQPs will have any quantum advantage over their classical counterparts. Here we critically investigate both the capabilities and performance of SQP networks by computing their effective dimension and effective capacity, as well as examining their performance on real learning problems. The results are compared to those obtained for other candidate networks which lack activation functions. It is found that simpler, and apparently easier-to-implement parametric quantum circuits actually perform better than SQPs. This indicates that the universal approximation theorem, which a cornerstone of the theory of classical neural networks, is not a relevant criterion for QNNs.
Quantum neural networks (QNN) have been proposed as a promising architecture for quantum machine learning. There exist a number of different quantum circuit designs being branded as QNNs, however no clear candidate has presented itself as more suitable than the others. Rather, the search for a ``quantum perceptron" -- the fundamental building block of a QNN -- is still underway. One candidate is quantum perceptrons designed to emulate the nonlinear activation functions of classical perceptrons. Such sigmoid quantum perceptrons (SQPs) inherit the universal approximation property that guarantees that classical neural networks can approximate any function. However, this does not guarantee that QNNs built from SQPs will have any quantum advantage over their classical counterparts. Here we critically investigate both the capabilities and performance of SQP networks by computing their effective dimension and effective capacity, as well as examining their performance on real learning problems. The results are compared to those obtained for other candidate networks which lack activation functions. It is found that simpler, and apparently easier-to-implement parametric quantum circuits actually perform better than SQPs. This indicates that the universal approximation theorem, which a cornerstone of the theory of classical neural networks, is not a relevant criterion for QNNs.
Quantum machine learning models based on parametrized quantum circuits, also called quantum neural networks (QNNs), are considered to be among the most promising candidates for applications on near-term quantum devices. Here we explore the expressivity and inductive bias of QNNs by exploiting an exact mapping from QNNs with inputs x to classical perceptrons acting on x⊗x (generalised to complex inputs). The simplicity of the perceptron architecture allows us to provide clear examples of the shortcomings of current QNN models, and the many barriers they face to becoming useful general-purpose learning algorithms. For example, a QNN with amplitude encoding cannot express the Boolean parity function for n≥3, which is but one of an exponential number of data structures that such a QNN is unable to express. Mapping a QNN to a classical perceptron simplifies training, allowing us to systematically study the inductive biases of other, more expressive embeddings on Boolean data. Several popular embeddings primarily produce an inductive bias towards functions with low class balance, reducing their generalisation performance compared to deep neural network architectures which exhibit much richer inductive biases. We explore two alternate strategies that move beyond standard QNNs. In the first, we use a QNN to help generate a classical DNN-inspired kernel. In the second we draw an analogy to the hierarchical structure of deep neural networks and construct a layered non-linear QNN that is provably fully expressive on Boolean data, while also exhibiting a richer inductive bias than simple QNNs. Finally, we discuss characteristics of the QNN literature that may obscure how hard it is to achieve quantum advantage over deep learning algorithms on classical data.
We demonstrate that it is possible to implement a quantum perceptron with a sigmoid activation function as an efficient, reversible many-body unitary operation. When inserted in a neural network, the perceptron's response is parameterized by the potential exerted by other neurons. We prove that such a quantum neural network is a universal approximator of continuous functions, with at least the same power as classical neural networks. While engineering general perceptrons is a challenging control problem —also defined in this work— the ubiquitous sigmoid-response neuron can be implemented as a quasi-adiabatic passage with an Ising model. In this construct, the scaling of resources is favorable with respect to the total network size and is dominated by the number of layers. We expect that our sigmoid perceptron will have applications also in quantum sensing or variational estimation of many-body Hamiltonians.
Abstract The field of artificial neural networks is expected to strongly benefit from recent developments of quantum computers. In particular, quantum machine learning, a class of quantum algorithms which exploit qubits for creating trainable neural networks, will provide more power to solve problems such as pattern recognition, clustering and machine learning in general. The building block of feed-forward neural networks consists of one layer of neurons connected to an output neuron that is activated according to an arbitrary activation function. The corresponding learning algorithm goes under the name of Rosenblatt perceptron. Quantum perceptrons with specific activation functions are known, but a general method to realize arbitrary activation functions on a quantum computer is still lacking. Here, we fill this gap with a quantum algorithm which is capable to approximate any analytic activation functions to any given order of its power series. Unlike previous proposals providing irreversible measurement–based and simplified activation functions, here we show how to approximate any analytic function to any required accuracy without the need to measure the states encoding the information. Thanks to the generality of this construction, any feed-forward neural network may acquire the universal approximation properties according to Hornik’s theorem. Our results recast the science of artificial neural networks in the architecture of gate-model quantum computers.
The development of quantum neural networks (QNNs) has attracted considerable attention due to their potential to surpass classical models in certain machine learning tasks. Nonetheless, it remains unclear under which conditions QNNs provide concrete benefits over classical neural networks (CNNs). This study addresses this question by performing both qualitative and quantitative analyses of classical and quantum models applied to regression problems, using two target functions with contrasting properties. Additionally, the work explores the methodological difficulties inherent in making fair comparisons between QNNs and CNNs. The findings reveal a distinct advantage of QNNs in a specific quantum machine learning context. In particular, QNNs excelled at approximating the sinusoidal function, achieving errors up to seven orders of magnitude lower than their classical counterparts. However, their performance was limited in other cases, emphasizing that QNNs are highly effective for certain tasks but not universally superior. These results reinforce the principles of the “No Free Lunch” theorem, highlighting that no single model outperforms all others across every problem domain.
Quantum machine learning (QML) is an emerging research area that combines quantum computation with classical machine learning (ML). The primary objective of QML is to enhance the performance of traditional ML algorithms by harnessing quantum phenomena. Inspired by the success of classical neural networks (NNs), their quantum analog, commonly known as quantum neural networks (QNNs), are widely being investigated. Despite the significant interest, the literature still lacks some concrete evidence about QNN's superiority over their classical counterparts, especially in practical applications. This paper empirically demonstrates a greater capacity in hybrid quantum neural networks (HQNNs) for a practical application, namely multi-class classification. In particular, we train both the HQNNs and their equivalent classical counterparts on the same data. We then benchmark the models' accuracy for quantifying model's capacity, where greater accuracy typically implies greater capacity. The results demonstrate a clear quantum advantage, i.e., greater capacity of HQNNs over their classical counterparts, where the HQNN models constantly achieve better accuracy. This superiority in performance by HQNNs serves as a foundational study for further investigation to magnify the quantum advantage in real-world applications of HQNNs.
Quantum Neural Networks (QNNs) have emerged as a promising avenue in the quest for next-generation machine learning capabilities.By harnessing the principles of quantum mechanics and quantum computing, QNNs offer the potential for exponential speedup and enhanced computational power compared to classical machine learning algorithms.This paper presents a comprehensive exploration of Quantum Neural Networks, covering their foundational concepts, various architectures, novel quantum-enhanced machine learning algorithms, practical implementations, advantages, and challenges.We begin with an overview of related work in Quantum Machine Learning, highlighting the achievements and progress in the field.Subsequently, we delve into the fundamental principles of Quantum Mechanics and Quantum Computing to provide a solid grounding for understanding QNNs.We then introduce the basics of Quantum Neural Networks, including quantum neurons, quantum gates, and quantum circuits for machine learning tasks.Various QNN architectures, such as Variational Quantum Circuits and Quantum Convolutional Neural Networks, are explored along with their potential applications.Additionally, quantum-enhanced machine learning algorithms, like Quantum Support Vector Machines and Quantum Generative Adversarial Networks, are discussed for a deeper understanding of QNN capabilities.Practical aspects, including hardware implementations, noise mitigation, and experimental results, are presented to shed light on the feasibility of QNNs in real-world scenarios.The paper concludes by discussing the advantages and challenges of Quantum Neural Networks and their potential implications for the future of machine learning and artificial intelligence.