org.kramerlab.autoencoder.neuralnet.rbm

DefaultRbmTrainingConfiguration

class DefaultRbmTrainingConfiguration extends RbmTrainingConfiguration

Implements a reasonable training strategy for Rbms.

Momentum and number of Gibbs-sampling steps are interpolated from their initial values to their final values by a sigmoid curve which is centered at the specified center and scaled with the specified factor (larger factor means that the change occurs more rapidly, smaller factor means that the change occurs more gradually)

Linear Supertypes
RbmTrainingConfiguration, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. DefaultRbmTrainingConfiguration
  2. RbmTrainingConfiguration
  3. AnyRef
  4. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new DefaultRbmTrainingConfiguration(epochs: Int = 128, minibatchSize: Int = 8, learningRate: Double = 0.01, initialBiasScaling: Double = 0.01, initialWeightScaling: Double = 0.001, initialMomentum: Double = 0.5, finalMomentum: Double = 0.875, initialGibbsSamplingSteps: Int = 1, finalGibbsSamplingSteps: Int = 2, sampleVisibleUnitsDeterministically: Boolean = false, weightPenaltyFactor: Double = 1.0E-5, gibbsSamplingStepsSteepness: Double = 1, sigmoidScalingFactor: Double = 1, interpolationCenter: Double = 0.5)

Value Members

  1. final def !=(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef

  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any

  3. final def ##(): Int

    Definition Classes
    AnyRef → Any

  4. final def ==(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef

  5. final def ==(arg0: Any): Boolean

    Definition Classes
    Any

  6. final def asInstanceOf[T0]: T0

    Definition Classes
    Any

  7. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  8. final def eq(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef

  9. def equals(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any

  10. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  11. final def getClass(): Class[_]

    Definition Classes
    AnyRef → Any

  12. def gibbsSamplingSteps(epoch: Int): Int

    Definition Classes
    DefaultRbmTrainingConfiguration → RbmTrainingConfiguration

  13. val gibbsSamplingStepsSteepness: Double

  14. def hashCode(): Int

    Definition Classes
    AnyRef → Any

  15. val interpolationCenter: Double

  16. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any

  17. def momentum(epoch: Int): Double

    Definition Classes
    DefaultRbmTrainingConfiguration → RbmTrainingConfiguration

  18. final def ne(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef

  19. final def notify(): Unit

    Definition Classes
    AnyRef

  20. final def notifyAll(): Unit

    Definition Classes
    AnyRef

  21. val sigmoidScalingFactor: Double

  22. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes
    AnyRef

  23. def toString(): String

    Definition Classes
    DefaultRbmTrainingConfiguration → AnyRef → Any

  24. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  25. final def wait(arg0: Long, arg1: Int): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  26. final def wait(arg0: Long): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  27. def weightPenalty(weights: Mat): Mat

    Definition Classes
    RbmTrainingConfiguration

Inherited from RbmTrainingConfiguration

Inherited from AnyRef

Inherited from Any

Ungrouped