Name
Abstract | ||
|---|---|---|
We introduce an exceptionally simple gated recurrent neural network (RNN) that achieves performance comparable to well-known gated architectures, such as LSTMs and GRUs, on the word-level language modeling task. We prove that our model has simple, predicable and non-chaotic dynamics. This stands in stark contrast to more standard gated architectures, whose underlying dynamical systems exhibit chaotic behavior. |
Year | Venue | Field |
|---|---|---|
2016 | international conference on learning representations | Computer science,Recurrent neural network,Dynamical systems theory,Predicable,Artificial intelligence,Chaotic,Machine learning,Language model |
DocType | Volume | Citations |
Journal | abs/1612.06212 | 1 |
PageRank | References | Authors |
0.35 | 0 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Laurent, Thomas | 1 | 74 | 7.43 |
| James H. von Brecht | 2 | 93 | 6.45 |