Generally, when asphalt concrete (AC) is in the design phase, the rutting development of the
actual pavement is always not considered. Traditional simulative wheel-tracking tests, which …

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical
need for techniques to rigorously introspect models and thereby ensure that they behave …

Explanation techniques that synthesize small, interpretable changes to a given image while
producing desired changes in the model prediction have become popular for introspecting …

Superpave mix design procedure is still empirical. Random and lengthy trials in a laboratory
during the design procedure can consume immense manpower and materials resources. To …

Accessible rapid COVID-19 testing continues to be necessary and several studies involving
deep neural network (DNN) methods for detection have been published. As part of a …

Despite their high accuracies, modern complex image classifiers cannot be trusted for
sensitive tasks due to their unknown decision-making process and potential biases …

Interpretability has emerged as a crucial aspect of building trust in machine learning
systems, aimed at providing insights into the working of complex neural networks that are …

Through the use of carefully tailored convolutional neural network architectures, a deep
image prior (DIP) can be used to obtain pre-images from latent representation encodings …

With the growing need for deploying deep models into critical decision-making, there is an
increased emphasis on explainability methods that can reveal intricate relationships …

With the surge in use of machine learning and deep learning models for critical decision
making in fields like healthcare, social justice and finance, the need to understand, debug …