Title | ||
---|---|---|
LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks. |
Abstract | ||
---|---|---|
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 changes in hidden state representations over time and noticed some interpretable patterns but also signifi... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TVCG.2017.2744158 | IEEE Transactions on Visualization and Computer Graphics |
Keywords | Field | DocType |
Tools,Recurrent neural networks,Visualization,Pattern matching,Computational modeling,Data models | Data mining,Data modeling,Use case,Visualization,Computer science,Recurrent neural network,Phrase structure rules,Artificial intelligence,Chord (music),Pattern matching,Computer graphics,Machine learning | Journal |
Volume | Issue | ISSN |
24 | 1 | 1077-2626 |
Citations | PageRank | References |
30 | 0.83 | 22 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hendrik Strobelt | 1 | 387 | 21.65 |
Sebastian Gehrmann | 2 | 84 | 10.58 |
Hanspeter Pfister | 3 | 5933 | 340.59 |
Alexander M. Rush | 4 | 1499 | 67.53 |