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.
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.
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.
Today, although there are studies for the active use of quantum computers, deep learning-based studies on quantum computing are few. Since the large amount of data needed by deep learning cannot be met from the literature, using deep learning in subjects such as quantum circuit optimization, and quantum circuit/algorithm generation challenges researchers. In this study, an approach is proposed to overcome the data and dataset deficiencies related to quantum circuits in the literature. The proposed approach generates datasets consisting of quantum circuits, truth tables of quantum circuits, unitary matrices, visuals, and pairs of these data. The circuits, data, and datasets produced with this approach have already been studied and are still being actively done. The performance of the proposed approach was evaluated as dependent on different variables and as elapsed time. With the proposed approach, circuits, data, and datasets with desired properties can be generated successfully. As a result, the contribution and performance of the proposed approach have been verified.
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.
In the field of image processing, a well-known model is the Convolutional Neural Network, or CNN. The unique benefit that sets this model apart is its exceptional ability to use the correlation information included in the data. Even with their amazing accomplishment, conventional CNNs could have trouble improving further in terms of generalization, accuracy, and computing economy. However, it could be challenging to train CNN correctly and process information quickly if the model or data dimensions are too large. This is since it will cause the data processing to lag. The Quantum Convolutional Neural Network, or QCNN for short, is a novel proposed quantum solution that might either enhance the functionality of an existing learning model or solve a problem requiring the combination of quantum computing with CNN. To highlight the flexibility and versatility of quantum circuits in improving feature extraction capabilities, this paper compares deep quantum circuit architecture designed for image-based tasks with classical Convolutional Neural Networks (CNNs) and a novel quantum circuit architecture. The covidx-cxr4 dataset was used to train quantum-CNN models, and their results were compared against those of other models. The results show that when paired with innovative feature extraction methods, the suggested deep Quantum Convolutional Neural Network (QCNN) outperformed the conventional CNN in terms of processing speed and recognition accuracy. Even though it required more processing time, QCNN outperformed CNN in terms of recognition accuracy. When training on the covidx-cxr4 dataset, this dominance becomes much more apparent, demonstrating how deeper quantum computing has the potential to completely transform image classification problems.
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 algorithms and models have made an impact in the area of AI and machine learning, one among them is CNN. CNN is extensively used in the area of image recognition and object detection for classification purposes. CNN is composed of several layers of filters to get feature maps of input data, yet foremost and crucial one is convolutional layer, hence the name Convolutional neural networks. However, the growth of quantum computing and quantum neural network in deep learning is limited. Three main obstacles that limit the growth of these are, first is due to the lack of real-time quantum computers to experiment with. Second is the improper training algorithms and at last, non-linearity nature of the neural networks. This paper introduces a novel approach to begin one's journey in quantum computing, along with solutions and developments. This work provides a detailed description of architectures, frameworks and algorithms used for implementing a QCNN model. The research was made regarding image recognition and object detection using QCNN and found that QCNN can increase the computational speeds with better performance metrics compared to classical computational methods. This paper also debates about applications of QCNN in computer vision, signal and image processing, Pharmaceuticals, Cryptography and various other fields. This study also explains Key players and future work in developing quantum computers, quantum computing algorithms, software and hardware support to implement QCNN in various applications.