keras_deep_bi_lstm: keras_deep_bi_lstm
In systats/deeplyr: Pretrained keras models for predicting ideology from tweets.

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

1
2
3

keras_deep_bi_lstm(input_dim, embed_dim = 128, seq_len = 50,
  hidden_dims = c(128, 64, 32), output_fun = "softmax",
  output_dim = 1)

`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)
`output_fun`	Output activation function
`output_dim`	Number of neurons of the output layer