kr.ac.kaist.ir.deep.fn

Activation

trait Activation extends (ScalarMatrix) ⇒ ScalarMatrix with Serializable

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
Serializable, Serializable, (ScalarMatrix) ⇒ ScalarMatrix, AnyRef, Any
Known Subclasses
HardSigmoid, HardTanh, HyperbolicTangent, Linear, Rectifier, Sigmoid, Softplus
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. Activation
  2. Serializable
  3. Serializable
  4. Function1
  5. AnyRef
  6. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Abstract Value Members

  1. abstract def apply(x: ScalarMatrix): ScalarMatrix

    Compute mapping for x

    Compute mapping for x

    x

    the input matrix. Before application, input should be summed already.

    returns

    value of f(x)

    Definition Classes
    Activation → Function1

  2. abstract def derivative(fx: ScalarMatrix): ScalarMatrix

    Compute differentiation value of this function at f(x) = fx

    Compute differentiation value of this function at f(x) = fx

    fx

    the output of this function

    returns

    differentiation value at f(x) = fx, which should be an square, diagonal matrix

Concrete Value Members

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

    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Definition Classes
    AnyRef → Any

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

    Definition Classes
    AnyRef → Any

  4. def andThen[A](g: (ScalarMatrix) ⇒ A): (ScalarMatrix) ⇒ A

    Definition Classes
    Function1
    Annotations
    @unspecialized()

  5. final def asInstanceOf[T0]: T0

    Definition Classes
    Any

  6. def clone(): AnyRef

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

  7. def compose[A](g: (A) ⇒ ScalarMatrix): (A) ⇒ ScalarMatrix

    Definition Classes
    Function1
    Annotations
    @unspecialized()

  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 hashCode(): Int

    Definition Classes
    AnyRef → Any

  13. def initialize(fanIn: Int, fanOut: Int, rows: Int = 0, cols: Int = 0): ScalarMatrix

    Initialize the weight matrix

    Initialize the weight matrix

    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

    rows

    the number of rows of resulting matrix (Default 0)

    cols

    the number of cols of resulting matrix (Default 0)

    returns

    the initialized weight matrix

  14. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any

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

    Definition Classes
    AnyRef

  16. final def notify(): Unit

    Definition Classes
    AnyRef

  17. final def notifyAll(): Unit

    Definition Classes
    AnyRef

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

    Definition Classes
    AnyRef

  19. def toString(): String

    Definition Classes
    Function1 → AnyRef → Any

  20. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from Serializable

Inherited from Serializable

Inherited from (ScalarMatrix) ⇒ ScalarMatrix

Inherited from AnyRef

Inherited from Any

Ungrouped