seq2feature_mds_stochastic: Feature extraction by stochastic mds
In ProcData: Process Data Analysis

Feature extraction by stochastic mds

1
2
3

seq2feature_mds_stochastic(seqs = NULL, K = 2,
  dist_type = "oss_action", max_epoch = 100, step_size = 0.01,
  pca = TRUE, tot = 1e-06, return_dist = FALSE, L_set = 1:3)

`seqs`	a `"proc"` object or a square matrix. If a squared matrix is provided, it is treated as the dissimilary matrix of a group of response processes.
`K`	the number of features to be extracted.
`dist_type`	a character string specifies the dissimilarity measure for two response processes. See 'Details'.
`max_epoch`	the maximum number of epochs for stochastic gradient descent.
`step_size`	the step size of stochastic gradient descent.
`pca`	a logical scalar. If `TRUE`, the principal components of the extracted features are returned.
`tot`	the accuracy tolerance for determining convergence.
`return_dist`	logical. If `TRUE`, the dissimilarity matrix will be returned. Default is `FALSE`.
`L_set`	length of ngrams considered.

seq2feature_mds_stochastic returns a list containing

`theta`	a numeric matrix giving the `K` extracted features or principal features. Each column is a feature.
`loss`	the value of the multidimensional scaling objective function.
`dist_mat`	the dissimilary matrix. This element exists only if `return_dist=TRUE`.