Related papers: PERTURB-c: Correlation Aware Perturbation Explaina…

Machine learning has become a key tool in cybersecurity, improving both attack strategies and defense mechanisms. Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated high accuracy in detecting malware…

For performing regression tasks involved in various physics problems, enhancing the precision or equivalently reducing the uncertainty of regression results is undoubtedly one of the central goals. Here, somewhat surprisingly, we find that…

While convolutional neural networks (CNNs) have found wide adoption as state-of-the-art models for image-related tasks, their predictions are often highly sensitive to small input perturbations, which the human vision is robust against.…

In some situations, the interpretability of the machine learning models plays a role as important as the model accuracy. Interpretability comes from the need to trust the prediction model, verify some of its properties, or even enforce them…

One of the hallmarks of active galactic nuclei are that they are highly variable with time. In watching the spectra vary it has been observed that the emission-lines often appear to "reverberate" -- that is they vary in response to…

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…

In this paper, we present a robust adaptive model predictive control (MPC) scheme for linear systems subject to parametric uncertainty and additive disturbances. The proposed approach provides a computationally efficient formulation with…

Machine learning-based intrusion detection requires complex models to capture patterns in high-dimensional, noisy, and class-imbalanced raw network traffic, yet deploying such models remains impractical on resource-constrained devices with…

Neural networks are a promising technique for parameterizing sub-grid-scale physics (e.g. moist atmospheric convection) in coarse-resolution climate models, but their lack of interpretability and reliability prevents widespread adoption.…

While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if…

Machine learning techniques, such as deep learning and ensemble methods, are widely used in various domains due to their ability to handle complex real-world tasks. However, their black-box nature has raised multiple concerns about the…

In recent years, machine learning models have been increasingly applied to spectroscopic datasets for chemical and biomedical analysis. For their successful adoption, particularly in clinical and safety-critical settings, professionals and…

This work studies the recursive robust principal components' analysis (PCA) problem. Here, "robust" refers to robustness to both independent and correlated sparse outliers, although we focus on the latter. A key application where this…

In this paper, we present YunMa, an exoplanet cloud simulation and retrieval package, which enables the study of cloud microphysics and radiative properties in exoplanetary atmospheres. YunMa simulates the vertical distribution and sizes of…

In modern human-robot collaboration (HRC) applications, multiple perception modules jointly extract visual, auditory, and contextual cues to achieve comprehensive scene understanding, enabling the robot to provide appropriate assistance to…

Explainability of black-box machine learning models is crucial, in particular when deployed in critical applications such as medicine or autonomous cars. Existing approaches produce explanations for the predictions of models, however, how…

In this article, we propose a data-driven methodology for combining the solutions of a set of competing turbulence models. The individual model predictions are linearly combined for providing an ensemble solution accompanied by estimates of…

Modern computer systems are highly configurable, with the total variability space sometimes larger than the number of atoms in the universe. Understanding and reasoning about the performance behavior of highly configurable systems, over a…

Autonomous cars have to navigate in dynamic environment which can be full of uncertainties. The uncertainties can come either from sensor limitations such as occlusions and limited sensor range, or from probabilistic prediction of other…

The inherent "black box" nature of deep neural networks (DNNs) compromises their transparency and reliability. Recently, explainable AI (XAI) has garnered increasing attention from researchers. Several perturbation-based interpretations…