fit_LSTM: Fit LSTM model
In stschn/deepANN: Neural Network Toolbox

fit_LSTM

R Documentation

Fit LSTM model

fit_LSTM is a wrapper function for fitting a LSTM model.

fit_LSTM(
  model,
  x,
  y,
  timesteps = 1L,
  batch_size = 1,
  epochs = 10,
  verbose = 1,
  validation_split = 0,
  cross_validation = NULL
)

`model`	A model object to train, e.g. returned by `build_LSTM`.
`x`	A feature data set, usually a matrix or data frame, returned by `get_LSTM_XY`.
`y`	An outcome data set, usually a vector, matrix or data frame, returned by `get_LSTM_XY`.
`timesteps`	A vector of timesteps for `x` and `y`. A feature does always have at least one timestep, but an outcome is either a scalar with one implicit timestep or a sequence with at least two timesteps. If only one value for `timesteps` is given, this value is used for the resampled feature tensor produced by `as_LSTM_X`. If two values are given, the first value is used as before and the second value for the resampled sequence or multi-step outcome tensor produced by `as_LSTM_Y`.
`batch_size`	Batch size, the number of samples per gradient update within training process.
`epochs`	Number of epochs to train the model.
`verbose`	Verbosity mode (0 = silent, 1 = progress bar, 2 = one line per epoch) determines how the training progress is visualized.
`validation_split`	Float between 0 and 1. Fraction of the training data used as validation data.
`cross_validation`	List or `NULL` (default). The list contains two elements whereby the first element stands for the number of folds (k) and the second element indicates the type `min` or `max` for quality measuring.

A trained model object.