I tried a bunch of things: The dangers of unexpected overfitting in classification of brain data

[Display omitted] •Neuroscience is rapidly adopting machine-learning in many forms.•Overfitting of parameters in machine-learning is well-known but also misunderstood.•Over-hyping can occur when analyses are optimized, and despite cross-validation.•Over-hyping threatens the integrity of the machine-...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neuroscience and biobehavioral reviews 2020-12, Vol.119, p.456-467
Hauptverfasser:	Hosseini, Mahan, Powell, Michael, Collins, John, Callahan-Flintoft, Chloe, Jones, William, Bowman, Howard, Wyble, Brad
Format:	Artikel
Sprache:	eng
Schlagworte:	Analysis Classification EEG Machine learning Overfitting Overhyping
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!