Abstract: This paper introduces a novel data-driven methodology named Evolutionary Polynomial Regression (EPR), which permits the multi-purpose modelling of physical phenomena, thr...
Orazio Giustolisi, Angelo Doglioni, D. A. Savic, B...
: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
The objective of image stabilization is to prevent or remove the motion blur degradation from images. We introduce a new approach to image stabilization based on combining informa...
— There are several types of processes which can be modeled explicitly by recording the interactions between a set of actors over time. In such applications, a common objective i...
In developing High-Performance Computing (HPC) software, time to solution is an important metric. This metric is comprised of two main components: the human effort required develo...