Poster
2024 workshop program
An Artificial Neural Network for on-board event pre-processing of Gamma-Ray Burst Observations
The work
Abstract
The aim is to have a Machine or Deep Learning model which can classify high-energetic (MeV to GeV range) astrophysical phenomena – with a particular focus on Gamma-Ray bursts and its potential progenitors. This model is planned to be implemented in a detector for on-the-fly predictions. At the moment, I pursue a feature-based classification: to derive new features from existing data, which are more distinctive and significant for the learning process of the AI. Within this project I test the performance on a large number of different models in Machine Learning and Deep Learning. Lastly, I want to modify my selection of the best models even further with Uncertainty Estimations and Quantifications.