- <init>
- build
- eps
Epsilon value for batch normalization; small floating point value added to
variance (algorithm 1 in
- decay
At test time: we can use a global estimate of the mean and variance, calculated
using a moving avera
- lockGammaBeta
If set to true: lock the gamma and beta parameters to the values for each
activation, specified by #
- minibatch
If doing minibatch training or not. Default: true. Under most circumstances,
this should be set to t
- nOut
- activation
- beta
Used only when 'true' is passed to #lockGammaBeta(boolean). Value is not used
otherwise.
Default: 0.
- gamma
Used only when 'true' is passed to #lockGammaBeta(boolean). Value is not used
otherwise.
Default: 1.
- momentum
- nIn