LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks

Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better understanding these models have studied the change...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on visualization and computer graphics 2018-01, Vol.24 (1), p.667-676
Hauptverfasser:	Strobelt, Hendrik, Gehrmann, Sebastian, Pfister, Hanspeter, Rush, Alexander M.
Format:	Artikel
Sprache:	eng
Schlagworte:	Annotations Computational modeling Data models LSTM Machine Learning Nesting Neural networks Pattern matching Progressions Recurrent neural networks Representations Statistical analysis Visualization
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!