Hangul Fonts Dataset: a Hierarchical and Compositional Dataset for Investigating Learned Representations

Hierarchy and compositionality are common latent properties in many natural and scientific datasets. Determining when a deep network's hidden activations represent hierarchy and compositionality is important both for understanding deep representation learning and for applying deep networks in d...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-06
Hauptverfasser:	Livezey, Jesse A, Hwang, Ahyeon, Yeung, Jacob, Bouchard, Kristofer E
Format:	Artikel
Sprache:	eng
Schlagworte:	Black boxes Coding Complexity Data analysis Datasets Domain names Fonts Hypotheses Learning Machine learning Representations Structural hierarchy Syllables Vowels
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!