Modules are normally designed to work on vectors.
The input variable x, which represents input data ,
is arranged so that the dimensions of the vector extend
in the first dimension (column) and additional colums
represent additional segments or samples.
The feature transformation is applied to each column
separately, so that for an input vector of dimension
will produce an output of dimension
. The row dimension is preserved. In addition,
the inout and output variable jout, the log J-function,
is a scalar for each column of , so is a row vector.
Additional dimensions are handled similarly.
For example, if is of dimension
, then will be of dimension
, and jout will be a
matrix.