kr.ac.kaist.ir.deep.train
Input Corruption: Drop input as zero.
If network uses drop-out training, we recommend that you do not use this.
probability of not-dropped. (default 95% = 0.95)
(default 95% = 0.95)
var corrupt = DroppingCorruption(presence = 0.99) var corrupted = corrupt(vector)
If the presence probability is P%, then this corruption leaves P% entries of the matrix
P%
Do corruption
Matrix to be corrupted
corrupted vector
probability of not-dropped.
Input Corruption: Drop input as zero.
If network uses drop-out training, we recommend that you do not use this.
probability of not-dropped.
(default 95% = 0.95)
If the presence probability is
P%
, then this corruption leavesP%
entries of the matrix