LSTM: LSTM

In Microsoft/CNTK-R: R Interface to the Microsoft Cognitive Toolkit (CNTK)

Description

Layer factory function to create an LSTM block for use inside a recurrence. The LSTM block implements one step of the recurrence and is stateless. It accepts the previous state as its first two arguments, and outputs its new state as a two-valued tuple (h,c).

Usage

LSTM(shape, cell_shape = NULL, activation = op_tanh,
  use_peepholes = FALSE, 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

Microsoft/CNTK-R documentation built on May 28, 2019, 1:52 p.m.