as_LSTM_X: Features (X) data format for LSTM

In stschn/deepANN: Neural Network Toolbox

Features (X) data format for LSTM

Description

Features (X) data format for LSTM

Usage

as_LSTM_X(x, timesteps = 1L)

Arguments

x	A feature data set, usually a matrix or data frame, returned by get_LSTM_XY.
timesteps	Number of timesteps; stands for the number of different periods within one sample (record) of the result, the resampled feature matrix x.

Value

A three-dimensional array of the resampled feature matrix x needed within Tensorflow for recurrent neural networks, e.g. LSTM.

1. dimension: Samples (s) = Number of records
   

2. dimension: Timesteps (t) = Number of different periods within one record
   

3. dimension: Features (f) = Number of features within a sequence of a period
   Note: A 3D-array with dimensions (s x t x f) can be interpret as f (s x t)-matrices.

See Also

get_LSTM_XY, as_LSTM_Y, as_tensor_3d.

Other Recurrent Neural Network (RNN): as_LSTM_Y(), as_LSTM_data_frame(), as_LSTM_period_outcome(), as_lag(), as_timesteps(), build_LSTM(), fit_LSTM(), get_LSTM_XY(), get_period_shift(), load_weights_ANN(), predict_ANN(), save_weights_ANN(), start_invert_differencing()

stschn/deepANN documentation built on June 25, 2024, 7:27 a.m.