kr.ac.kaist.ir.deep.layer

Layer

trait Layer extends (ScalarMatrix) ⇒ ScalarMatrix with Serializable

Trait that describes layer-level computation

Layer is an instance of ScalaMatrix => ScalaMatrix function. Therefore "layers" can be composed together.

Linear Supertypes
Serializable, Serializable, (ScalarMatrix) ⇒ ScalarMatrix, AnyRef, Any
Known Subclasses
BasicLayer, DropoutOperation, FullTensorLayer, NormalizeOperation, Rank3TensorLayer, ReconBasicLayer, Reconstructable, SplitTensorLayer
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. Layer
  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 val W: IndexedSeq[ScalarMatrix]

    weights for update

    weights for update

    returns

    weights

  2. abstract val act: Activation

    Activation Function

    Activation Function

    Attributes
    protected

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

    Forward computation

    Forward computation

    x

    input matrix

    returns

    output matrix

    Definition Classes
    Layer → Function1

  4. abstract val dW: IndexedSeq[ScalarMatrix]

    accumulated delta values

    accumulated delta values

    returns

    delta-weight

  5. abstract def toJSON: JsObject

    Translate this layer into JSON object (in Play! framework)

    Translate this layer into JSON object (in Play! framework)

    returns

    JSON object describes this layer

  6. abstract def updateBy(error: ScalarMatrix, input: ScalarMatrix, output: ScalarMatrix): ScalarMatrix

    Backward computation.

    Backward computation.

    error

    to be propagated ( dG / dF is propagated from higher layer )

    input

    of this layer (in this case, x = entry of dX / dw)

    output

    of this layer (in this case, y)

    returns

    propagated error (in this case, dG/dx )

    Attributes
    protected[kr.ac.kaist.ir.deep]
    Note

    Let this layer have function F composed with function X(x) = W.x + b and higher layer have function G.

    Weight is updated with: dG/dW and propagate dG/dx

    For the computation, we only used denominator layout. (cf. Wikipedia Page of Matrix Computation) For the computation rules, see "Matrix Cookbook" from MIT.

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 into_:(x: ScalarMatrix): ScalarMatrix

    Sugar: Forward computation.

    Sugar: Forward computation. Calls apply(x)

    x

    input matrix

    returns

    output matrix

    Attributes
    protected[kr.ac.kaist.ir.deep]

  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