Ali Mosleh

Marawan Gamal Abdel Hameed, Ali Mosleh, Marzieh S. Tahaei et al.

While convolutional neural networks (CNNs) have become the de facto standard for most image processing and computer vision applications, their deployment on edge devices remains challenging. Tensor decomposition methods provide a means of compressing CNNs to meet the wide range of device constraints by imposing certain factorization structures on their convolution tensors. However, being limited to the small set of factorization structures presented by state-of-the-art decomposition approaches can lead to sub-optimal performance. We propose SeKron, a novel tensor decomposition method that offers a wide variety of factorization structures, using sequences of Kronecker products. By recursively finding approximating Kronecker factors, we arrive at optimal decompositions for each of the factorization structures. We show that SeKron is a flexible decomposition that generalizes widely used methods, such as Tensor-Train (TT), Tensor-Ring (TR), Canonical Polyadic (CP) and Tucker decompositions. Crucially, we derive an efficient convolution projection algorithm shared by all SeKron structures, leading to seamless compression of CNN models. We validate SeKron for model compression on both high-level and low-level computer vision tasks and find that it outperforms state-of-the-art decomposition methods.

Ali Mosleh, Faraz Ali, Fengjia Zhang et al.

Digital zoom on smartphones relies on learning-based super-resolution (SR) models that operate on RAW sensor images, but obtaining sensor-specific training data is challenging due to the lack of ground-truth images. Synthetic data generation via ``unprocessing'' pipelines offers a potential solution by simulating the degradations that transform high-resolution (HR) images into their low-resolution (LR) counterparts. However, these pipelines can introduce domain gaps due to incomplete or unrealistic degradation modeling. In this paper, we demonstrate that principled and carefully designed degradation modeling can enhance SR performance in real-world conditions. Instead of relying on generic priors for camera blur and noise, we model device-specific degradations through calibration and unprocess publicly available rendered images into the RAW domain of different smartphones. Using these image pairs, we train a single-image RAW-to-RGB SR model and evaluate it on real data from a held-out device. Our experiments show that accurate degradation modeling leads to noticeable improvements, with our SR model outperforming baselines trained on large pools of arbitrarily chosen degradations.

Fahimeh Fakour, Ali Mosleh, Ramin Ramezani

The adaptation and use of Machine Learning (ML) in our daily lives has led to concerns in lack of transparency, privacy, reliability, among others. As a result, we are seeing research in niche areas such as interpretability, causality, bias and fairness, and reliability. In this survey paper, we focus on a critical concern for adaptation of ML in risk-sensitive applications, namely understanding and quantifying uncertainty. Our paper approaches this topic in a structured way, providing a review of the literature in the various facets that uncertainty is enveloped in the ML process. We begin by defining uncertainty and its categories (e.g., aleatoric and epistemic), understanding sources of uncertainty (e.g., data and model), and how uncertainty can be assessed in terms of uncertainty quantification techniques (Ensembles, Bayesian Neural Networks, etc.). As part of our assessment and understanding of uncertainty in the ML realm, we cover metrics for uncertainty quantification for a single sample, dataset, and metrics for accuracy of the uncertainty estimation itself. This is followed by discussions on calibration (model and uncertainty), and decision making under uncertainty. Thus, we provide a more complete treatment of uncertainty: from the sources of uncertainty to the decision-making process. We have focused the review of uncertainty quantification methods on Deep Learning (DL), while providing the necessary background for uncertainty discussion within ML in general. Key contributions in this review are broadening the scope of uncertainty discussion, as well as an updated review of uncertainty quantification methods in DL.

Taotao Zhou, Xiaoge Zhang, Enrique Lopez Droguett et al.

In this paper, we leverage the recent advances in physics-informed neural network (PINN) and develop a generic PINN-based framework to assess the reliability of multi-state systems (MSSs). The proposed methodology consists of two major steps. In the first step, we recast the reliability assessment of MSS as a machine learning problem using the framework of PINN. A feedforward neural network with two individual loss groups are constructed to encode the initial condition and state transitions governed by ordinary differential equations (ODEs) in MSS. Next, we tackle the problem of high imbalance in the magnitude of the back-propagated gradients in PINN from a multi-task learning perspective. Particularly, we treat each element in the loss function as an individual task, and adopt a gradient surgery approach named projecting conflicting gradients (PCGrad), where a task's gradient is projected onto the norm plane of any other task that has a conflicting gradient. The gradient projection operation significantly mitigates the detrimental effects caused by the gradient interference when training PINN, thus accelerating the convergence speed of PINN to high-precision solutions to MSS reliability assessment. With the proposed PINN-based framework, we investigate its applications for MSS reliability assessment in several different contexts in terms of time-independent or dependent state transitions and system scales varying from small to medium. The results demonstrate that the proposed PINN-based framework shows generic and remarkable performance in MSS reliability assessment, and the incorporation of PCGrad in PINN leads to substantial improvement in solution quality and convergence speed.

Taotao Zhou, Enrique Lopez Droguett, Ali Mosleh et al.

There has been a growing interest in deep learning-based prognostic and health management (PHM) for building end-to-end maintenance decision support systems, especially due to the rapid development of autonomous systems. However, the low trustworthiness of PHM hinders its applications in safety-critical assets when handling data from an unknown distribution that differs from the training dataset, referred to as the out-of-distribution (OOD) dataset. To bridge this gap, we propose an uncertainty-informed framework to diagnose faults and meanwhile detect the OOD dataset, enabling the capability of learning unknowns and achieving trustworthy fault diagnosis. Particularly, we develop a probabilistic Bayesian convolutional neural network (CNN) to quantify both epistemic and aleatory uncertainties in fault diagnosis. The fault diagnosis model flags the OOD dataset with large predictive uncertainty for expert intervention and is confident in providing predictions for the data within tolerable uncertainty. This results in trustworthy fault diagnosis and reduces the risk of erroneous decision-making, thus potentially avoiding undesirable consequences. The proposed framework is demonstrated by the fault diagnosis of bearings with three OOD datasets attributed to random number generation, an unknown fault mode, and four common sensor faults, respectively. The results show that the proposed framework is of particular advantage in tackling unknowns and enhancing the trustworthiness of fault diagnosis in safety-critical applications.

Hamed S Nejad, Tarannom Parhizkar, Ali Mosleh

The classical approach to design a system is based on a deterministic perspective where the assumption is that the system and its environment are fully predictable, and their behaviour is completely known to the designer. Although this approach may work fairly well for regular design problems, it is not satisfactory for the design of highly sensitive and complex systems where significant resources and even lives are at risk. In addition it can results in extra costs of over-designing for the sake of safety and reliability. In this paper, a risk-based design framework using Simulation Based Probabilistic Risk Assessment (SIMPRA) methodology is proposed. SIMPRA allows the designer to use the knowledge that can be expected to exist at the design stage to identify how deviations can occur; and then apply these high-level scenarios to a rich simulation model of the system to generate detailed scenarios and identify the probability and consequences of these scenarios. SIMPRA has three main modules including Simulator, Planner and Scheduler, and it approach is much more efficient in covering the large space of possible scenarios as compared with, for example, biased Monte Carlo simulations because of the Planner module which uses engineering knowledge to guide the simulation process. The value-added of this approach is that it enables the designer to observe system behaviour under many different conditions. This process will lead to a risk-informed design in which the risk of negative consequences is either eliminated entirely or reduced to an acceptable range. For illustrative purposes, an earth observation satellite system example is introduced.

Marawan Gamal Abdel Hameed, Marzieh S. Tahaei, Ali Mosleh et al.

Modern Convolutional Neural Network (CNN) architectures, despite their superiority in solving various problems, are generally too large to be deployed on resource constrained edge devices. In this paper, we reduce memory usage and floating-point operations required by convolutional layers in CNNs. We compress these layers by generalizing the Kronecker Product Decomposition to apply to multidimensional tensors, leading to the Generalized Kronecker Product Decomposition (GKPD). Our approach yields a plug-and-play module that can be used as a drop-in replacement for any convolutional layer. Experimental results for image classification on CIFAR-10 and ImageNet datasets using ResNet, MobileNetv2 and SeNet architectures substantiate the effectiveness of our proposed approach. We find that GKPD outperforms state-of-the-art decomposition methods including Tensor-Train and Tensor-Ring as well as other relevant compression methods such as pruning and knowledge distillation.

Tarannom Parhizkar, Theresa Stewart, Lixian Huang et al.

A cyber physical human complex system failure prevents the accomplishment of the systems intended function. The failure of a complex system could be a breakdown of any system hardware, human related factors, application software, or the interaction between these components. Having knowledge about all these three components would allow us to better understand the behavior, interactions, and the associated failure mechanisms of the cyber physical human systems as a whole. In this study, degradation mechanisms in these three components are classified and discussed. The main categories are hardware related degradation mechanisms including mechanical, thermal, chemical, electronic and radiation effects degradation mechanisms. In addition to hardware related degradation mechanisms, human failure modes, software errors, and the failures due to cyber physical human interactions are presented and discussed. This paper covers the main types of failure mechanisms in complex systems and is beneficial for developing conceptual risk and reliability models for complex systems.

Taotao Zhou, Enrique Lopez Droguett, Ali Mosleh

Considerable research has been devoted to deep learning-based predictive models for system prognostics and health management in the reliability and safety community. However, there is limited study on the utilization of deep learning for system reliability assessment. This paper aims to bridge this gap and explore this new interface between deep learning and system reliability assessment by exploiting the recent advances of physics-informed deep learning. Particularly, we present an approach to frame system reliability assessment in the context of physics-informed deep learning and discuss the potential value of physics-informed generative adversarial networks for the uncertainty quantification and measurement data incorporation in system reliability assessment. The proposed approach is demonstrated by three numerical examples involving a dual-processor computing system. The results indicate the potential value of physics-informed deep learning to alleviate computational challenges and combine measurement data and mathematical models for system reliability assessment.