Calculates the neuron output with the sigmoid function either from the real
value or binary input saved in the list dataList.
sigmUnitFuncSwitch(rbm, dataList, biases, weights, runParams)A instance of the class RBM.
A list with the data matrices for the calculations.
The biases for the calculations
The weight matrix for the calculations
Parameters which indicates the status of the training.
"actualCD" and "finishCD" are needed
(see trainRBM)
The real value and binary activations for the units
The return value is a list with the output of the sigmoid function
as first entry and binary representation calculated through a comparison of
the output with random numbers. The random numbers a generated with the
function runif.
If the parameter runParams["actualCD"] or runParams["finishCD"]
is equal one, the calculation is made with the real value data
(dataList[[1]]), otherwise with the binary representations
(dataList[[2]]).
Other RBM unit functions: linearUnitFunc;
sigmUnitFunc