ProcData (version 0.2.5)

aseq2feature_seq2seq: Feature Extraction by action sequence autoencoder

Description

aseq2feature_seq2seq extract features from action sequences by action sequence autoencoder.

Usage

aseq2feature_seq2seq(aseqs, K, rnn_type = "lstm", n_epoch = 50,
  method = "last", step_size = 1e-04, optimizer_name = "adam",
  samples_train, samples_valid, samples_test = NULL, pca = TRUE,
  gpu = FALSE, parallel = FALSE, seed = 12345, verbose = TRUE,
  return_theta = TRUE)

Arguments

aseqs

a list of n action sequences. Each element is an action sequence in the form of a vector of actions.

K

the number of features to be extracted.

rnn_type

the type of recurrent unit to be used for modeling response processes. "lstm" for the long-short term memory unit. "gru" for the gated recurrent unit.

n_epoch

the number of training epochs for the autoencoder.

method

the method for computing features from the output of an recurrent neural network in the encoder. Available options are "last" and "avg".

step_size

the learning rate of optimizer.

optimizer_name

a character string specifying the optimizer to be used for training. Availabel options are "sgd", "rmsprop", "adadelta", and "adam".

samples_train

vectors of indices specifying the training, validation and test sets for training autoencoder.

samples_valid

vectors of indices specifying the training, validation and test sets for training autoencoder.

samples_test

vectors of indices specifying the training, validation and test sets for training autoencoder.

pca

logical. If TRUE, the principal components of features are returned. Default is TRUE.

gpu

logical. If TRUE, use gpu for training when available. Default is FALSE.

parallel

logical. If TRUE, allow cpu parallel computing. Default is FALSE.

seed

random seed.

verbose

logical. If TRUE, training progress is printed.

return_theta

logical. If TRUE, extracted features are returned.

Value

aseq2feature_seq2seq returns a list containing

theta

a matrix containing K features or principal features. Each column is a feature.

train_loss

a vector of length n_epoch recording the trace of training losses.

valid_loss

a vector of length n_epoch recording the trace of validation losses.

test_loss

a vector of length n_epoch recording the trace of test losses. Exists only if samples_test is not NULL.

Details

This function trains a sequence-to-sequence autoencoder using keras. The encoder of the autoencoder consists of an embedding layer and a recurrent neural network. The decoder consists of another recurrent neural network and a fully connect layer with softmax activation. The outputs of the encoder are the extracted features.

The output of the encoder is a function of the encoder recurrent neural network. It is the last output of the encoder recurrent neural network if method="last" and the average of the encoder recurrent nenural network if method="avg".

See Also

chooseK_seq2seq for choosing K through cross-validation.

Other feature extraction methods: atseq2feature_seq2seq, seq2feature_mds_large, seq2feature_mds, seq2feature_seq2seq, tseq2feature_seq2seq

Examples

# NOT RUN {
n <- 50
seqs <- seq_gen(n)
seq2seq_res <- aseq2feature_seq2seq(seqs$action_seqs, 5, rnn_type="lstm", n_epoch=5, 
                                   samples_train=1:40, samples_valid=41:50)
features <- seq2seq_res$theta
plot(seq2seq_res$train_loss, col="blue", type="l")
lines(seq2seq_res$valid_loss, col="red")
# }