Standard Pointing Model meets Deep-Learning

Placeholder TBC A study to examine the potential benefits of applying Deep-learning methods, specifically Feedforward Neural Networks (FNN) instead or in conjunction with traditional Static Pointing Error Models (SPEMs) for astronomical instruments' Blind Pointing Error compensation. Ambitious project like the ongoing study for the Atacama Large Aperture Submillimeter Telescope (AtLAST) inspired to investigate possible improvements of traditional Blind Pointing Error Modeling. The study assesses the practicality and applicability of FNNs by applying them to data from real instruments in operation