keras_deep_lstm: keras deep lstm

In systats/textlearnR:

Description

Word embedding + Deep (bidirectional) long short-term memory

Usage

keras_deep_lstm(input_dim, embed_dim = 128, seq_len = 50,
  hidden_dims = c(128, 64, 32), bidirectional = F,
  output_fun = "softmax", output_dim = 2)

Arguments

input_dim	Number of unique vocabluary/tokens
embed_dim	Number of word vectors
seq_len	Length of the input sequences
hidden_dims	Number of neurons per layer as vector of integers c(256, 128, 64)
bidirectional	default is F
output_fun	Output activation function
output_dim	Number of neurons of the output layer

Details

Stacking lstm modules of different size.

Value

keras model

systats/textlearnR documentation built on May 6, 2019, 8:31 p.m.