Despite the successful results they have provided, the need of high computational power is the biggest obstacle in front of deep learning. In this study, the pooling operation that is used many times in a deep learning network is carried out with quantum circuits. In order to make able testing of the proposed circuits on today's quantum computers, binary inputs are used. In today's technology, it is not able to run whole deep learning process on reliable quantum computers. But, when it is possible to perform all deep learning steps much faster on quantum computers, it will eliminate the need to use pre-trained networks. With training the deep learning networks from scratch in much shorter time, a new era will start for deep learning. In this study, quantum binary pooling circuits are proposed for this purpose. Quantum circuits are proposed for 3, 4, 5, and 9-dimensional windows. In today's quantum computers that do not work iteratively, the proposed circuit only works for 1 step. In order to apply pooling to the whole image, the circuit must be looped. With the development of the relevant quantum computer architecture, the method will become applicable to the whole image.
Despite the successful results they have provided, the need of high computational power is the biggest obstacle in front of deep learning. In this study, the pooling operation that is used many times in a deep learning network is carried out with quantum circuits. In order to make able testing of the proposed circuits on today's quantum computers, binary inputs are used. In today's technology, it is not able to run whole deep learning process on reliable quantum computers. But, when it is possible to perform all deep learning steps much faster on quantum computers, it will eliminate the need to use pre-trained networks. With training the deep learning networks from scratch in much shorter time, a new era will start for deep learning. In this study, quantum binary pooling circuits are proposed for this purpose. Quantum circuits are proposed for 3, 4, 5, and 9-dimensional windows. In today's quantum computers that do not work iteratively, the proposed circuit only works for 1 step. In order to apply pooling to the whole image, the circuit must be looped. With the development of the relevant quantum computer architecture, the method will become applicable to the whole image.
Deep learning is used in different research topics and draws attention with its successful results. Today, the resource need of deep learning, which requires much data and resources, is tried to be met by technologies such as parallel processors and graphic processors. In this study, the convolution process, which is one of the main causes of resource need in deep learning, is performed with quantum circuits. Thanks to the convolution process run on quantum computers, whose computation speeds are many times higher than supercomputers, the training step of deep learning can be performed much faster. In this way, the need for performance, which is one of the biggest obstacles in front of deep learning and forces researchers to work on pre-trained networks, will be met. With running deep learning networks on quantum computers, it is predicted by the scientific world that a new era for deep learning will start. Although we propose quantum circuits for the convolution process with 2, 3, and 4 window sizes, it can be used for only one iteration today. However, with obtaining structures such as quantum ram and developing sequential processing architecture for quantum computers, the proposed circuits can be used for a complete convolution process.
The resource need for deep learning and quantum computers' high computing power potential encourage collaboration between the two fields. Today, variational quantum circuits are used to perform the convolution operation with quantum computing. However, the results produced by variational circuits do not show a direct resemblance to the classical convolution operation. Because classical data is encoded into quantum data with their exact values in value-encoded methods, in contrast to variational quantum circuits, arithmetical operations can be applied with high accuracy. In this study, value-encoded quantum circuits for convolution and pooling operations are proposed to apply deep learning in quantum computers in a traditional and proven way. To construct the convolution and pooling operations, some modules such as addition, multiplication, division, and comparison are created. In addition, a window-based framework for quantum image processing applications is proposed. The generated convolution and pooling circuits are simulated on the IBM QISKIT simulator in parallel thanks to the proposed framework. The obtained results are verified by the expected results. Due to the limitations of quantum simulators and computers in the NISQ era, the used grayscale images are resized to 8x8 and the resolution of the images is reduced to 3 qubits. With developing the quantum technologies, the proposed approach can be applied for bigger and higher resolution images. Although the proposed method causes more qubit usage and circuit depth compared to variational convolutional circuits, the results they produce are exactly the same as the classical convolution process.
Quantum computing is a new computational paradigm that promises applications in several fields, including machine learning. In the last decade, deep learning, and in particular Convolutional neural networks (CNN), have become essential for applications in signal processing and image recognition. Quantum deep learning, however remains a challenging problem, as it is difficult to implement non linearities with quantum unitaries. In this paper we propose a quantum algorithm for applying and training deep convolutional neural networks with a potential speedup. The quantum CNN (QCNN) is a shallow circuit, reproducing completely the classical CNN, by allowing non linearities and pooling operations. The QCNN is particularly interesting for deep networks and could allow new frontiers in image recognition, by using more or larger convolution kernels, larger or deeper inputs. We introduce a new quantum tomography algorithm with ℓ∞ norm guarantees, and new applications of probabilistic sampling in the context of information processing. We also present numerical simulations for the classification of the MNIST dataset to provide practical evidence for the efficiency of the QCNN.
Quantum computing in general and quantum deep learning represent a promising field relatedto the research of modern methods and algorithms of quantum computing used for the purposeof teaching and developing new architectures of artificial neural networks. Recently, therehas been a trend that research conducted in the field of quantum deep learning is becoming increasinglywidespread among specialists. This can be explained by the fact that it has been establishedthat quantum circuits are capable of functioning like artificial neural networks, whiledemonstrating the best results in solving several tasks, including, for example, the actual task ofclassifying objects in an image or in a video stream. Thanks to the rapid development of quantumcomputing in the field of deep learning, optimal solutions have been found for such urgent problemsas the vanishing gradient problem, finding a local minimum, improving the efficiency oflarge-scale parametric machine learning algorithms, eliminating decoherence and quantum errors,etc. Within the framework of this work, the process of functioning of a quantum variationalscheme is described, its main characteristics are established, and disadvantages are identified.The key features of quantum computing, on which the process of implementing quantum deeplearning with the reinforcement of a convolutional neural network is based, are also analyzed. Inaddition, quantum deep learning of a convolutional neural network has been carried out using avariational quantum scheme, which leads to an increase in the performance of a convolutionalneural network in solving the problem of image processing, namely its classification, using aquantum computing environment. The relevance of this article consists in the implementation of aquantum deep learning algorithm with the reinforcement of a convolutional neural network forimage processing, as well as the great importance of the subject of this study for the future developmentof quantum computing devices that can be used in artificial intelligence systems, etc.,which corresponds to the priority direction of the development of domestic science.
Deep learning is one of the most successful and far-reaching strategies used in machine learning today. However, the scale and utility of neural networks is still greatly limited by the current hardware used to train them. These concerns have become increasingly pressing as conventional computers quickly approach physical limitations that will slow performance improvements in years to come. For these reasons, scientists have begun to explore alternative computing platforms, like quantum computers, for training neural networks. In recent years, variational quantum circuits have emerged as one of the most successful approaches to quantum deep learning on noisy intermediate scale quantum devices. We propose a hybrid quantum-classical neural network architecture where each neuron is a variational quantum circuit. We empirically analyze the performance of this hybrid neural network on a series of binary classification data sets using a simulated universal quantum computer and a state of the art universal quantum computer. On simulated hardware, we observe that the hybrid neural network achieves roughly 10% higher classification accuracy and 20% better minimization of cost than an individual variational quantum circuit. On quantum hardware, we observe that each model only performs well when the qubit and gate count is sufficiently small.
Tremendous progress has been witnessed in artificial intelligence within the domain of neural network backed deep learning systems and its applications. As we approach the post Moore’s Law era, the limit of semiconductor fabrication technology along with a rapid increase in data generation rates have lead to an impending growing challenge of tackling newer and more modern machine learning problems. In parallel, quantum computing has exhibited rapid development in recent years. Due to the potential of a quantum speedup, quantum based learning applications have become an area of significant interest, in hopes that we can leverage quantum systems to solve classical problems. In this work, we propose a quantum deep learning architecture; we demonstrate our quantum neural network architecture on tasks ranging from binary and multi-class classification to generative modelling. Powered by a modified quantum differentiation function along with a hybrid quantum-classic design, our architecture encodes the data with a reduced number of qubits and generates a quantum circuit, loading it onto a quantum platform where the model learns the optimal states iteratively. We conduct intensive experiments on both the local computing environment and IBM-Q quantum platform. The evaluation results demonstrate that our architecture is able to outperform Tensorflow-Quantum by up to 12.51% and 11.71% for a comparable classic deep neural network on the task of classification trained with the same network settings. Furthermore, our GAN architecture runs the discriminator and the generator purely on quantum hardware and utilizes the swap test on qubits to calculate the values of loss functions. In comparing our quantum GAN, we note our architecture is able to achieve similar performance with 98.5% reduction on the parameter set when compared to classical GANs. With the same number of parameters, additionally, QuGAN outperforms other quantum based GANs in the literature for up to 125.0% in terms of similarity between generated distributions and original data sets.