Attention Model

AttentionModel(attention_dim, attention_span = NULL, attention_axis = NULL,
  init = init_glorot_uniform(), go_backwards = FALSE,
  enable_self_stabilization = TRUE, name = "")

Arguments

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