A Survey on Knowledge Editing of Neural Networks

Deep neural networks are becoming increasingly pervasive in academia and industry, matching and surpassing human performance in a wide variety of fields and related tasks. However, just as humans, even the largest artificial neural networks (ANNs) make mistakes, and once-correct predictions can beco...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2024-11, p.1-17
Hauptverfasser:	Mazzia, Vittorio, Pedrani, Alessandro, Caciolai, Andrea, Rottmann, Kay, Bernardi, Davide
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Computational modeling Continual learning Data models knowledge editing (KE) Metalearning model editing Neural networks neural networks editing Predictive models Reliability Reviews Surveys Taxonomy
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!