Related papers: DIM-SUM: Dynamic IMputation for Smart Utility Mana…
Diffusion models have recently shown promise in time series forecasting, particularly for probabilistic predictions. However, they often fail to achieve state-of-the-art point estimation performance compared to regression-based methods.…
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about…
Industrial maintenance is being transformed by the Internet of Things and edge computing, generating continuous data streams that demand real-time, adaptive decision-making under limited computational resources. While data stream mining…
This paper introduces KZImputer, a novel adaptive imputation method for univariate time series designed for short to medium-sized missed points (gaps) (1-5 points and beyond) with tailored strategies for segments at the start, middle, or…
This study investigates a method to evaluate time-series datasets in terms of the performance of deep neural networks (DNNs) with state space models (deep SSMs) trained on the dataset. SSMs have attracted attention as components inside DNNs…
Detecting and interpreting operator actions, engagement, and object interactions in dynamic industrial workflows remains a significant challenge in human-robot collaboration research, especially within complex, real-world environments.…
Processing-In-Memory (PIM) is a novel approach that augments existing DRAM memory chips with lightweight logic. By allowing to offload computations to the PIM system, this architecture allows for circumventing the data-bottleneck problem…
Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…
Many environments currently employ machine learning models for data processing and analytics that were built using a limited number of training data points. Once deployed, the models are exposed to significant amounts of previously-unseen…
Multi-step time-series prediction is an essential supportive step for decision-makers in several industrial areas. Artificial intelligence techniques, which use a neural network component in various forms, have recently frequently been used…
Recent advances in self-supervised learning have led to the development of foundation models that have significantly advanced performance in various computer vision tasks. However, despite their potential, these models often overlook the…
The ability to estimate epistemic uncertainty is often crucial when deploying machine learning in the real world, but modern methods often produce overconfident, uncalibrated uncertainty predictions. A common approach to quantify epistemic…
We present a framework that leverages the Discrete Empirical Interpolation Method (DEIM) for interpretable deep learning and dynamical system analysis. Although DEIM efficiently approximates nonlinear terms in projection-based reduced-order…
Cyberattacks can cause a severe impact on power systems unless detected early. However, accurate and timely detection in critical infrastructure systems presents challenges, e.g., due to zero-day vulnerability exploitations and the…
Single Index Models (SIMs) are simple yet flexible semi-parametric models for machine learning, where the response variable is modeled as a monotonic function of a linear combination of features. Estimation in this context requires learning…
The burgeoning navigation services using digital maps provide great convenience to drivers. Nevertheless, the presence of anomalies in lane rendering map images occasionally introduces potential hazards, as such anomalies can be misleading…
Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…
Background: Existing guidelines for handling missing data are generally not consistent with the goals of prediction modelling, where missing data can occur at any stage of the model pipeline. Multiple imputation (MI), often heralded as the…
Coherent Ising Machines (CIMs) have emerged as a hybrid form of quantum computing devices designed to solve NP-complete problems, offering an exciting opportunity for discovering optimal solutions. Despite challenges such as susceptibility…
Symbolic music generation is a challenging task in multimedia generation, involving long sequences with hierarchical temporal structures, long-range dependencies, and fine-grained local details. Though recent diffusion-based models produce…