Layer factory function to create a plain RNN block for use inside a recurrence. The RNN block implements one step of the recurrence and is stateless. It accepts the previous state as its first argument, and outputs its new state.

RRNStep(shape, cell_shape = NULL, activation = op_sigmoid,
  init = init_glorot_uniform(), init_bias = 0,
  enable_self_stabilization = FALSE, name = "")

Arguments

shape

- list of ints representing tensor shape

activation

(Function) - optional activation Function

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

init

(scalar or matrix or initializer, defaults to init_glorot_uniform()) – initial value of weights W_bias