Table 1 The main structures and parameters of DeepACLSTM
Layer Type | Size | NP |
|---|---|---|
embedding | 21 | 441 |
Convolution1D | 1 × 42 | 1806 |
Convolution2D | 3 × 1 | 168 |
Dropout1 | 0.5 | 0 |
FC 1 | 400 | 706,000 |
\({LSTM}_f^1\) | 300 | 841,200 |
\({LSTM}_b^1\) | 300 | 841,200 |
\({LSTM}_f^2\) | 300 | 721,200 |
\({LSTM}_b^2\) | 300 | 721,200 |
Dropout2 | 0.4 | 0 |
FC 2 | 600 | 600,600 |
Softmax | 8 | 4808 |