Aus IPD-Institutsseminar
Version vom 19. Mai 2021, 07:54 Uhr von Clemens Müssener (Diskussion | Beiträge)
(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Zur Navigation springen Zur Suche springen
Termin (Alle Termine)
Datum Fr 11. Juni 2021, 11:30 Uhr
Dauer 30 min
Vorheriger Termin Fr 21. Mai 2021
Nächster Termin Fr 18. Juni 2021


Vortragende(r) Philipp Weinmann
Titel Tuning of Explainable ArtificialIntelligence (XAI) tools in the field of textanalysis
Vortragstyp Bachelorarbeit
Betreuer(in) Clemens Müssener
Kurzfassung The goal of this bachelor thesis was to analyse classification results using a 2017 published method called shap. Explaining how an artificial neural network makes a decision is an interdisciplinary research subject combining computer science, math, psychology and philosophy. We analysed these explanations from a psychological standpoint and after presenting our findings we will propose a method to improve the interpretability of text explanations using text-hierarchies, without loosing much/any accuracy. Secondary, the goal was to test out a framework developed to analyse a multitude of explanation methods. This Framework will be presented next to our findings and how to use it to create your own analysis. This Bachelor thesis is addressed at people familiar with artificial neural networks and other machine learning methods.
Neuen Vortrag erstellen