Trait

com.github.nearbydelta.deepspark.data

Activation

Related Doc: package data

Permalink

trait Activation extends Differentiable

Trait that describes an activation function for each layer

Because these activation functions can be shared, we recommend to make inherited one as an object.

Linear Supertypes
Differentiable, (DataVec) ⇒ DataVec, Serializable, Serializable, AnyRef, Any
Known Subclasses
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. Activation
  2. Differentiable
  3. Function1
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show all
Visibility
  1. Public
  2. All

Abstract Value Members

  1. abstract def apply(v1: DataVec): DataVec

    Permalink
    Definition Classes
    Function1
  2. abstract def derivative(fx: DataVec): Matrix

    Permalink

    Differentiate function at output value fx.

    Differentiate function at output value fx.

    fx

    Differentiation point vector, by output value.

    returns

    Differentiation value of this function, generally squared matrix with same dimension.

    Definition Classes
    Differentiable

Concrete 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. def andThen[A](g: (DataVec) ⇒ A): (DataVec) ⇒ A

    Permalink
    Definition Classes
    Function1
    Annotations
    @unspecialized()
  5. final def asInstanceOf[T0]: T0

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

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  7. def compose[A](g: (A) ⇒ DataVec): (A) ⇒ DataVec

    Permalink
    Definition Classes
    Function1
    Annotations
    @unspecialized()
  8. def diffAtY(y: DataVec): Matrix

    Permalink

    Differentiate function at output value y.

    Differentiate function at output value y.

    y

    Differentiation point vector, by output value.

    returns

    Differentiation value of this function, generally squared matrix with same dimension.

    Definition Classes
    Differentiable
  9. final def eq(arg0: AnyRef): Boolean

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

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

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

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

    Permalink
    Definition Classes
    AnyRef → Any
  14. def initialize(fanIn: Int, fanOut: Int): (Double, Double)

    Permalink

    Initialization range of weight

    Initialization range of weight

    fanIn

    the number of fan-in i.e. the number of neurons in previous layer

    fanOut

    the number of fan-out i.e. the number of neurons in next layer

    returns

    the initialized range of weight

  15. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  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
    Function1 → 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 Differentiable

Inherited from (DataVec) ⇒ DataVec

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped