Name
Title | ||
|---|---|---|
Recurrent Neural Networks With External Addressable Long-Term and Working Memory for Learning Long-Term Dependences. |
Abstract | ||
|---|---|---|
Learning long-term dependences (LTDs) with recurrent neural networks (RNNs) is challenging due to their limited internal memories. In this paper, we propose a new external memory architecture for RNNs called an external addressable long-term and working memory (EALWM)-augmented RNN. This architecture has two distinct advantages over existing neural external memory architectures, namely the division of the external memory into two parts—long-term memory and working memory—with both addressable and the capability to learn LTDs without suffering from vanishing gradients with necessary assumptions. The experimental results on algorithm learning, language modeling, and question answering demonstrate that the proposed neural memory architecture is promising for practical applications. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/TNNLS.2019.2910302 | IEEE transactions on neural networks and learning systems |
Keywords | Field | DocType |
Recurrent neural networks,Logic gates,Random access memory,Memory architecture,Microprocessors | Architecture,Question answering,Computer science,Working memory,Recurrent neural network,Artificial intelligence,Language model,Memory architecture,Machine learning,Auxiliary memory | Journal |
Volume | Issue | ISSN |
31 | 3 | 2162-237X |
Citations | PageRank | References |
3 | 0.38 | 8 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhibin Quan | 1 | 16 | 2.65 |
| Weili Zeng | 2 | 3 | 1.05 |
| Xuelian Li | 3 | 3 | 0.38 |
| Yandong Liu | 4 | 3 | 0.38 |
| Yunxiu Yu | 5 | 3 | 0.72 |
| Wankou Yang | 6 | 199 | 26.33 |