Attention Model
AttentionModel(attention_dim, attention_span = NULL, attention_axis = NULL, init = init_glorot_uniform(), go_backwards = FALSE, enable_self_stabilization = TRUE, name = "")
init | (scalar or matrix or initializer, defaults to init_glorot_uniform()) – initial value of weights W |
---|---|
name | string (optional) the name of the Function instance in the network |