Introduction. The development of quantum computing and artificial intelligence necessitates the development of hybrid quantum-classical algorithms for solving complex computational problems. The relevance of the research is due to the need for new approaches to making creative AI decisions in conditions of exhaustion of training samples. (QVA) based on weak measurements with fuzzy filtering of input data is a promising research direction. The article first proposes a quantum variational autoencoder (QVA) based on weak measurements, which expands the space of possible solutions due to quantum effects – qubit entanglement, superposition of states and information teleportation. A fundamentally important modification is the introduction of weak measurements, which provide information about the quantum system with minimal impact on its state. The purpose of the article is to improve AI through modeling of autoencoder algorithms using weak measurements and fuzzy logic. Results. For the first time, numerical simulation of KVA based on weak measurements with fuzzy filtering was performed on classical computers and cloud services. The quality of KVA reconstruction is comparable to classical autoencoders. The simulation was performed for a one-dimensional signal, since for the CIFAR-10 and MNIST training samples, the simulation requires more than 5 petabytes of RAM. The KVA runtime in Google Colab was approximately 40 seconds. Conclusions. The integration of the fuzzy filtering mechanism into the KVA structure expands the capabilities of processing distorted and incomplete data. Such a modification increases the model's resistance to thermal noise and input data artifacts, improving the quality of information compression. Fuzzy clustering allows the system to effectively operate with ambiguous situations under conditions of uncertainty. Computer simulations have shown that adapting the fuzzy membership function to the type of input data, increasing the number of latent variables, and selecting the learning rate of the neural network can improve the quality of the reconstruction of the input signal. Keywords: quantum computing, neural network, variational autoencoder, fuzzy logic, weak measurements.
Introduction. The development of quantum computing and artificial intelligence necessitates the development of hybrid quantum-classical algorithms for solving complex computational problems. The relevance of the research is due to the need for new approaches to making creative AI decisions in conditions of exhaustion of training samples. (QVA) based on weak measurements with fuzzy filtering of input data is a promising research direction. The article first proposes a quantum variational autoencoder (QVA) based on weak measurements, which expands the space of possible solutions due to quantum effects – qubit entanglement, superposition of states and information teleportation. A fundamentally important modification is the introduction of weak measurements, which provide information about the quantum system with minimal impact on its state. The purpose of the article is to improve AI through modeling of autoencoder algorithms using weak measurements and fuzzy logic. Results. For the first time, numerical simulation of KVA based on weak measurements with fuzzy filtering was performed on classical computers and cloud services. The quality of KVA reconstruction is comparable to classical autoencoders. The simulation was performed for a one-dimensional signal, since for the CIFAR-10 and MNIST training samples, the simulation requires more than 5 petabytes of RAM. The KVA runtime in Google Colab was approximately 40 seconds. Conclusions. The integration of the fuzzy filtering mechanism into the KVA structure expands the capabilities of processing distorted and incomplete data. Such a modification increases the model's resistance to thermal noise and input data artifacts, improving the quality of information compression. Fuzzy clustering allows the system to effectively operate with ambiguous situations under conditions of uncertainty. Computer simulations have shown that adapting the fuzzy membership function to the type of input data, increasing the number of latent variables, and selecting the learning rate of the neural network can improve the quality of the reconstruction of the input signal. Keywords: quantum computing, neural network, variational autoencoder, fuzzy logic, weak measurements.
Variational Autoencoders (VAEs) are fundamental for generative modeling and image reconstruction, yet their performance often struggles to maintain high fidelity in reconstructions. This study introduces a hybrid model, Quantum Variational Autoencoder (Q-VAE), which integrates quantum encoding within the encoder while utilizing fully connected layers to extract meaningful representations. The decoder uses transposed convolution layers for up-sampling. The Q-VAE is evaluated against the classical VAE and the classical direct-passing VAE, which utilizes windowed pooling filters. Results on the MNIST and USPS datasets demonstrate that Q-VAE consistently outperforms classical approaches, achieving lower Fréchet Inception Distance scores, thereby indicating superior image fidelity and enhanced reconstruction quality. These findings highlight the potential of Q-VAE for high-quality synthetic data generation and improved image reconstruction in generative models.
The emerging intersection of quantum computing and large scale data processing is generally referred to an early research field named as Quantum-Assisted Artificial Intelligence (QAAI).The goal of this research is to integrate quantum algorithms with commonly used AI models, so as to tackle computational bottlenecks in dealing with large amounts of data.Some well known quantum algorithms, for the classification problem for example one can mention Quantum Support Vector Machines (QSVM) and Quantum Nearest Neighbor Methods can offer improvement in the classification accuracy at the cost of having a substantially smaller computational complexity.This is achieved with the proposed methodology of using variational quantum circuits for optimizing learning parameters and hybrid quantum classical architectures for efficient training of the model.Experiment results show that the complexity of datasets could be accelerated by 30-40% in training speed while comparable accuracy could be retained compared with its traditional AI counterpart.Furthermore, randomized measurement protocol is implemented to improve the system's performance in dealing with high dimensional data with low resource overhead.In addition, the integration of QAAI models includes greater resilience in the presence of noisy input data.This enabled us to develop providing more effective solutions for big data analytics, financial forecasting, and real time decision making system.This, however, still remains to be done, as integrating quantum-enhanced data encoding strategies for running quantum algorithms and exploring new frameworks for quantum assisted learning can make QAAI solutions an effective way to tackle the aforementioned scaling issues that all classical AI systems have.
Abstract Classical autoencoders are neural networks that can learn efficient low-dimensional representations of data in higher-dimensional space. The task of an autoencoder is, given an input x , to map x to a lower dimensional point y such that x can likely be recovered from y . The structure of the underlying autoencoder network can be chosen to represent the data on a smaller dimension, effectively compressing the input. Inspired by this idea, we introduce the model of a quantum autoencoder to perform similar tasks on quantum data. The quantum autoencoder is trained to compress a particular data set of quantum states, where a classical compression algorithm cannot be employed. The parameters of the quantum autoencoder are trained using classical optimization algorithms. We show an example of a simple programmable circuit that can be trained as an efficient autoencoder. We apply our model in the context of quantum simulation to compress ground states of the Hubbard model and molecular Hamiltonians.
The article is devoted to the study of the possibility of uncertainty processing using quantum algorithms. Uncertainty processing is one of the most important tasks in artificial intelligence. The quality of knowledge used by the intelligent system depends on the solution of this problem. Domain knowledge contains uncertainty. The paper considers the possibility of uncertainty handling using quantum computing. Tensor method is used to represent uncertainty. The tensor method provides an object representation of fuzzy knowledge. This approach allows to investigate the properties of uncertainty which are not available in representing fuzzy knowledge by traditional methods such as fuzzy sets, Bayesian networks, Stanford confidence factor, neural networks. Tensor processing on a classical computer is a computationally complex task. Quantum algorithms provide exponential acceleration in solving such problems. The article discusses the possibility of using quantum algorithms to process fuzzy knowledge represented by tensors.
The concept of an autoencoder is a key element of modern machine learning methods. It is used, e.g., to compress the input data into a lower-dimensional representation, which is later employed in other machine learning algorithms. In the area of quantum computing application methods, quantum machine learning is also developing dynamically, with the concept of a quantum autoencoder also present. In the article, we discuss a variant of building a quantum autoencoder based on a quantum convolutional network. The proposed autoencoder is characterized by an architecture based on adjacent quantum gates, which is especially important for the near-future noisy intermediate-scale hardware implementation of such a type of quantum circuits. The proposed circuits are built with an elementary set of gates, i.e., controlled negation gates and rotation gates. The described architecture of a quantum autoencoder properly uses the quantum phenomenon called quantum exponential capacitys, i.e., a linear number of qubits which allow encoding an exponential amount of classical information. In our case, for n qubit, it is possible to encode a classical gray coloured image with dimensionality 2n × 2n. The conducted numerical experiments on a set image of handwritten characters and letters show that, for a small number of parameters, the quantum autoencoder offers a reconstruction quality comparable to the currently used classical autoencoders. An important assumption is the omission of additional dimensionality reduction techniques, e.g., PCA, for the preparation of classical data. In the discussed experiment, the data after reconstruction can be read directly from the quantum register, through a series of quantum register measurements.
In recent years, machine learning and deep learning have driven advances in domains such as image classification, speech recognition, and anomaly detection by leveraging multi-layer neural networks to model complex data. Simultaneously, quantum computing (QC) promises to address classically intractable problems via quantum parallelism, motivating research in quantum machine learning (QML). Among QML techniques, quantum autoencoders show promise for compressing high-dimensional quantum and classical data. However, designing effective quantum circuit architectures for quantum autoencoders remains challenging due to the complexity of selecting gates, arranging circuit layers, and tuning parameters.
This paper proposes a neural architecture search (NAS) framework that automates the design of quantum autoencoders using a genetic algorithm (GA). By systematically evolving variational quantum circuit (VQC) configurations, our method seeks to identify high-performing hybrid quantum-classical autoencoders for data reconstruction without becoming trapped in local minima. We demonstrate effectiveness on image datasets, highlighting the potential of quantum autoencoders for efficient feature extraction within a noise-prone, near-term quantum era. Our approach lays a foundation for broader application of genetic algorithms to quantum architecture search, aiming for a robust, automated method that can adapt to varied data and hardware constraints.