Abstract Combining machine learning and quantum computation is a potential path towards powerful applications on quantum devices. Among such approaches, quantum neural networks have emerged as a promising framework. In this work, we present a novel architecture for dissipative quantum neural networks (DQNNs) in which each building block can implement any quantum channel, thus introducing a clear notion of universality suitable for the quantum framework. To this end, we reformulate DQNNs using isometries instead of the conventionally used unitaries, thereby reducing the number of parameters in these models. We furthermore derive a versatile one-to-one parametrization of isometries, facilitating the practical implementation of the proposed structure. Focusing on the impact of different objective functions on the optimization process, we numerically investigate the trainability of extended DQNNs. Our results identify the Hilbert-Schmidt distance as a readily measurable cost function that enables efficient and reliable model optimization. These findings advance both the theoretical understanding and the experimental implementability of quantum neural networks.
Abstract Combining machine learning and quantum computation is a potential path towards powerful applications on quantum devices. Among such approaches, quantum neural networks have emerged as a promising framework. In this work, we present a novel architecture for dissipative quantum neural networks (DQNNs) in which each building block can implement any quantum channel, thus introducing a clear notion of universality suitable for the quantum framework. To this end, we reformulate DQNNs using isometries instead of the conventionally used unitaries, thereby reducing the number of parameters in these models. We furthermore derive a versatile one-to-one parametrization of isometries, facilitating the practical implementation of the proposed structure. Focusing on the impact of different objective functions on the optimization process, we numerically investigate the trainability of extended DQNNs. Our results identify the Hilbert-Schmidt distance as a readily measurable cost function that enables efficient and reliable model optimization. These findings advance both the theoretical understanding and the experimental implementability of quantum neural networks.
Quantum computing is one of the most exciting research areas of the last decades. At the same time, methods of machine learning have started to dominate science, industry and our everyday life. In this thesis we combine these two essential research topics of the 21st century and introduce dissipative quantum neural networks (DQNNs), which are designed for fully quantum learning tasks, are capable of universal quantum computation and have low memory requirements while training. We start the discussion of this interdisciplinary topic by introducing artificial neural networks, which are a very common tool in classical machine learning. Next, we give an overview on quantum information. Here we focus on quantum algorithms and circuits, which are used to implement quantum neural networks. Moreover, we explain the opportunities and challenges arising with today's quantum computers. The discussion of the architecture and training algorithm of the DQNNs forms the core of this work. These networks are optimised with training data pairs in form of input and desired output states and therefore can be used for characterising unknown or untrusted quantum devices. We not only demonstrate the generalisation behaviour of these quantum neural networks using classical simulations, but also implement them successfully on actual quantum computers. To understand the ultimate limits for such quantum machine learning methods, we discuss the quantum no free lunch theorem, which describes a bound on the probability that a quantum device, which can be modelled as a unitary process and is optimised with quantum examples, gives an incorrect output for a random input. This gives us a tool to review the learning behaviour of quantum neural networks in general and the DQNNs in particular. Moreover we expand the area of applications of DQNNs in two directions. In the first case, we include additional information beyond just the training data pairs: since quantum devices are always structured, the resulting data is always structured as well. We modify the DQNN's training algorithm such that knowledge about the graph-structure of the training data pairs is included in the training process and show that this can lead to better generalisation behaviour. Both the original DQNN and the DQNN including graph structure are trained with data pairs in order to characterise an underlying relation. However, in the second extension of the algorithm we aim to learn characteristics of a set of quantum states in order to extend it to quantum states which have similar properties. Therefore we build a generative adversarial model where two DQNNs, called the generator and discriminator, are trained in a competitive way. Overall, we observe that DQNNs can not only be trained efficiently but also, similar to their classical counterparts, modified to suit different applications.
Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we call dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed. Our work represents the first rigorous analysis of the scalability of a perceptron-based QNN.
The advent of noisy intermediate-scale quantum (NISQ) devices offers crucial opportunities for the development of quantum algorithms. Here we evaluate the noise tolerance of two quantum neural network (QNN) architectures on IBM's NISQ devices, namely, dissipative QNN (DQNN) whose building-block perceptron is a completely positive map, and the quantum approximate optimization algorithm (QAOA). We compare these two approaches to learning an unknown unitary. While both networks succeed in this learning task, we find that a DQNN learns an unknown unitary more reliably than QAOA and is less susceptible to gate noise.
Artificial intelligence has been transformed by deep neural networks, yet the search for new learning architectures continues. Quantum machine learning offers one such direction, and hybrid quantum neural networks, which combine classical neural-network components with quantum information processing units, have emerged as a practical framework for near-term quantum technologies. However, the rapid development of the field across diverse architectures, benchmarks and hardware assumptions makes it difficult to assess the utility of various proposals, identify where genuine advantages may arise, and determine how practitioners can use these models. While recent benchmarks caution that such gains have not yet been demonstrated at scale, theoretical work has identified tasks on which quantum models hold provable advantages, and hybrid approaches have delivered promising results on practical problems using deliberately compact quantum components and substantially fewer trainable parameters. Here, we review hybrid quantum neural networks for the machine-learning and quantum-machine-learning communities. We summarize their main theoretical and methodological foundations, survey some of the most promising architectures developed so far, and examine their implementation challenges and reported performance. By consolidating these perspectives, this review provides a structured view of the state of the field and helps identify promising paths for future research and application-driven development.
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.
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.