Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

To achieve its full predictive potential, a digital twin must consistently and accurately reflect
its physical counterpart throughout its operational lifetime. To this end, the inverse map** …

Abstract As Deep Neural Networks (DNN) make their way into safety-critical decision
processes, it becomes imperative to have robust and reliable uncertainty estimates for their …

Because of the curse of dimensionality, the data in high-dimensional space hardly afford
sufficient information for neural networks training. Hence, this is a tough task to approximate …

Malware authors focus on deceiving and evading Anti Malware Engines (AME). Evasion
attacks take in malware samples and modify those samples to by-pass ml based AME …

When training large flexible models, practitioners often rely on grid search to select
hyperparameters that control over-fitting. This grid search has several disadvantages: the …

Deep learning's immense capabilities are often constrained by the complexity of its models,
leading to an increasing demand for effective sparsification techniques. Bayesian …

A number of popular transfer learning methods rely on grid search to select regularization
hyperparameters that control over-fitting. This grid search requirement has several key …

As Deep Neural Networks are increasingly being utilized in safety-critical domains,
assessing the uncertainty of the models during inference will be a crucial component in …

Generating high-quality random numbers with a Gaussian probability distribution function is
an important and resource-consuming computational task for many applications in the fields …