Package | Description |
---|---|
org.apache.ignite.ml.nn |
Contains neural networks and related classes.
|
Modifier and Type | Method and Description |
---|---|
MLPTrainer<P> |
MLPTrainer.withArchSupplier(IgniteFunction<Dataset<EmptyContext,SimpleLabeledDatasetData>,MLPArchitecture> archSupplier)
Set up the multilayer perceptron architecture supplier that defines layers and activators.
|
MLPTrainer<P> |
MLPTrainer.withBatchSize(int batchSize)
Set up the batch size (per every partition).
|
MLPTrainer<P> |
MLPTrainer.withEnvironmentBuilder(LearningEnvironmentBuilder envBuilder)
Changes learning Environment.
|
MLPTrainer<P> |
MLPTrainer.withLocIterations(int locIterations)
Set up the maximal number of local iterations before synchronization.
|
MLPTrainer<P> |
MLPTrainer.withLoss(IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss)
Set up the loss function to be minimized during the training.
|
MLPTrainer<P> |
MLPTrainer.withMaxIterations(int maxIterations)
Set up the maximal number of iterations before the training will be stopped.
|
MLPTrainer<P> |
MLPTrainer.withSeed(long seed)
Set up the multilayer perceptron model initializer.
|
MLPTrainer<P> |
MLPTrainer.withUpdatesStgy(UpdatesStrategy<? super MultilayerPerceptron,P> updatesStgy)
Set up the update strategy that defines how to update model parameters during the training.
|
GridGain In-Memory Computing Platform : ver. 8.9.14 Release Date : November 5 2024