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

Word embedding + long short-term memory + GPU

keras_cudnn_lstm(input_dim, embed_dim = 128, seq_len = 50,
  filter_size = 5, n_filters = 100, pool_size = 4, lstm_dim = 64,
  bidirectional = F, dropout = 0.2, output_dim = 1,
  output_fun = "sigmoid")

`input_dim`	Number of unique vocabluary/tokens
`embed_dim`	Number of word vectors
`seq_len`	Length of the input sequences
`lstm_dim`	Number of recurrent neurons (default 64)
`output_dim`	Number of neurons of the output layer
`output_fun`	Output activation function
`lstm_drop`	Recurrent dropout ratio