Research Article
Hierarchical Self-Attention Hybrid Sparse Networks for Document Classification
Table 1
Total parameters in variant RNNs models.
| | Model | GRU | | Variant 1 | Variant 2 | Variant 3 | Normal | | Parameter | | | | |
| | Model | LSTM | | Variant 1 | Variant 2 | Variant 3 | Normal | | Parameter | | | | |
|
|
