AttentionLayer
AttentionLayer[] represents a trainable net layer that learns to pay attention to certain portions of its input.
AttentionLayer[net] specifies a particular net to give scores for portions of the input.
AttentionLayer[net, opts] includes options for weight normalization, masking and other parameters.
Examples
Create an attention layer:
AttentionLayer[]Please visit the official Wolfram Language Reference for more details.