Design Space Exploration of Hybrid Quantum–Classical Neural Networks

The unprecedented success of classical neural networks and the recent advances in quantum computing have motivated the research community to explore the interplay between these two technologies, leading to the so-called quantum neural networks. In fact, universal quantum computers are anticipated to both speed up and improve the accuracy of neural networks. However, whether such quantum neural networks will result in a clear advantage on noisy intermediate-scale quantum (NISQ) devices is still not clear. In this paper, we propose a systematic methodology for designing quantum layer(s) in hybrid quantum–classical neural network (HQCNN) architectures. Following our proposed methodology, we develop different variants of hybrid neural networks and compare them with pure classical architectures of equivalent size. Finally, we empirically evaluate our proposed hybrid variants and show that the addition of quantum layers does provide a noticeable computational advantage.

Methodology for Ensuring a Comfortable Microclimate State in a Smart Home Using an Ensemble of Fuzzy Artificial Neural Networks

Analysis of the application of smart home technology indicates an insufficient level of controllability of its infrastructure, which leads to excessive consumption of energy and information resources. The problem of managing the digital infrastructure of human living space, is associated with a large number of highly specialized solutions for home automation, which complicate the management process. Smart home is considered as a set of independent cyber-physical devices aimed at achieving its goal. For coordinated work of cyber-physical devices it is proposed to provide their joint work through a single information center. Simulation of device operation modes in a digital environment preserves the resource of physical devices by making a virtual calculation for all possible variants of interaction of devices between themselves and the physical environment. A methodology for controlling the microclimate of a smart home using an ensemble of fuzzy artificial neural networks is developed, with the example of joint use of air conditioning, ventilation and heating. The neural network algorithm allows you to monitor the parameters of the physical environment, predict the modes of cyber-physical devices and generate control signals for each of them, ensuring the joint operation of devices with minimal resource consumption and information traffic. A variant of practical implementation of a smart home climate control system on the example of a multifunctional educational computer class is proposed. Hybrid neural networks of air conditioning, ventilation and heating systems were developed. The testing of the microclimate control system of a multifunctional university classroom using hybrid neural networks was carried out, a programmable logic controller of domestic production was used as a control device. The goal of management based on cooperating cyber-physical devices is to achieve a minimum of power and information traffic when they work together.

Ensemble of Hybrid Neural Networks to Compensate for Epistemic Uncertainties: A Case Study in System Prognosis

In this contribution, a case study considering an unexpected corrosion-fatigue crack propagation issue in an aircraft fleet is used to discuss how to compensate for incomplete knowledge in time dependent responses integration and extrapolation. For the considered application, degradation resulting from mechanical fatigue is well understood and accounted in the damage models. However, the unexpected corrosion effects are not accounted in damage integration, yielding a large discrepancy between predicted and observed crack lengths. To address this epistemic uncertainty in the fleet damage accumulation model, hybrid neural networks cells are formulated; where physics-informed layers address well-understood aspects of the degradation, and data-driven layers are trained to act as correction terms. The considered case study encompasses highly imbalanced data sets with uncertainties acting asynchronously. To improve overall accuracy, ensemble learning techniques are adapted to merge the resulting hybrid neural network cells predictions. Lastly, a heuristic based on optimal ensemble weights is presented to help in the decision-making task of defining safe operation of the fleet. Results show that our proposed approach was capable of compensating for the epistemic uncertainties, and that the proposed heuristic can be used to rank aircraft damage severity, allowing to prioritize aircraft for inspection and/or route reassignment.