| Package | Description |
|---|---|
| de.jungblut.classification.nn |
| Modifier and Type | Method and Description |
|---|---|
RBM.RBMBuilder |
RBM.RBMBuilder.batchParallelism(int numThreads) |
static RBM.RBMBuilder |
RBM.RBMBuilder.create(ActivationFunction activation,
int... layer)
Creates a new
RBM.RBMBuilder from an activation function and
layersizes. |
RBM.RBMBuilder |
RBM.RBMBuilder.lambda(double lambda)
Sets the regularization parameter lambda, defaults to 0 if not set.
|
RBM.RBMBuilder |
RBM.RBMBuilder.miniBatchSize(int size) |
RBM.RBMBuilder |
RBM.RBMBuilder.stochastic()
Sets the training mode to stochastic.
|
RBM.RBMBuilder |
RBM.RBMBuilder.stochastic(boolean stochastic)
If verbose is true, stochastic training will be used.
|
RBM.RBMBuilder |
RBM.RBMBuilder.trainingType(TrainingType type)
Sets the training type, it defaults to CPU- so only use if you want to
use the GPU.
|
RBM.RBMBuilder |
RBM.RBMBuilder.verbose()
Sets verbose to true.
|
RBM.RBMBuilder |
RBM.RBMBuilder.verbose(boolean verbose)
If verbose is true, progress indicators will be printed to STDOUT.
|
Copyright © 2016. All rights reserved.