Class

com.github.cloudml.zen.ml.neuralNetwork

EquilibratedUpdater

Related Doc: package neuralNetwork

Permalink

class EquilibratedUpdater extends Updater

Equilibrated Gradient Descent the paper: RMSProp and equilibrated adaptive learning rates for non-convex optimization

Annotations
@Experimental()
Linear Supertypes
Updater, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. EquilibratedUpdater
  2. Updater
  3. Serializable
  4. Serializable
  5. AnyRef
  6. Any
  1. Hide All
  2. Show all
Visibility
  1. Public
  2. All

Instance Constructors

  1. new EquilibratedUpdater(epsilon: Double, momentum: Double)

    Permalink

Value Members

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

    Permalink
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  4. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  5. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  6. def compute(weightsOld: Vector, gradient: Vector, stepSize: Double, iter: Int, regParam: Double): (Vector, Double)

    Permalink
    Definition Classes
    EquilibratedUpdater → Updater
  7. val epsilon: Double

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

    Permalink
    Definition Classes
    AnyRef
  9. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  10. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  11. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  12. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  13. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  14. def l2(weightsOld: Vector, gradient: Vector, stepSize: Double, iter: Int, regParam: Double): Double

    Permalink
    Attributes
    protected
  15. val momentum: Double

    Permalink
  16. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  17. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  18. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  19. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  20. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any
  21. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  22. final def wait(arg0: Long, arg1: Int): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  23. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from Updater

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped