Benutzer: Gast  Login
Titel:

Demystification of Flat Minima and Generalisability of Deep Neural Networks

Dokumenttyp:
Konferenzbeitrag
Art des Konferenzbeitrags:
Poster
Autor(en):
Shen, Hao; Gottwald, Martin
Abstract:
Among many unsolved puzzles in theories of Deep Neural Networks (DNNs), generalisability is arguably one of the most puzzling mysteries of DNNs. In this work, we investigates the concept of sharpness/flatness of local minima of the error function, and its relationship to generalisability of DNNs. By defining the sharpness of local minima as the largest Eigenvalue of the Hessian, we identify four influencing factors contributing to the sharpness, while three factors are also found for controlli...     »
Dewey-Dezimalklassifikation:
620 Ingenieurwissenschaften
Kongress- / Buchtitel:
International Conference on Machine Learning
Kongress / Zusatzinformationen:
Understanding and Improving Generalization in Deep Learning
Datum der Konferenz:
14 Juni 2019
Jahr:
2019
Quartal:
2. Quartal
Jahr / Monat:
2019-06
Monat:
Jun
Reviewed:
ja
Sprache:
en
WWW:
ICML 2019 Workshop Paper 67
TUM Einrichtung:
Lehrstuhl für Datenverarbeitung
Letzte Änderung:
02.08.2022
 BibTeX