| Package | Description |
|---|---|
| org.deeplearning4j.nn.conf.layers.recurrent | |
| org.deeplearning4j.nn.params |
| Class and Description |
|---|
| Bidirectional |
| Bidirectional.Builder |
| Bidirectional.Mode
This Mode enumeration defines how the activations for the forward and backward networks should be combined.
ADD: out = forward + backward (elementwise addition) MUL: out = forward * backward (elementwise multiplication) AVERAGE: out = 0.5 * (forward + backward) CONCAT: Concatenate the activations. Where 'forward' is the activations for the forward RNN, and 'backward' is the activations for the backward RNN. |
| SimpleRnn |
| SimpleRnn.Builder |
| Class and Description |
|---|
| Bidirectional |
Copyright © 2022. All rights reserved.