kr.ac.kaist.ir.deep.layer

ReconBasicLayer

class ReconBasicLayer extends BasicLayer with Reconstructable

Layer : Reconstructable Basic Layer

Linear Supertypes
Reconstructable, BasicLayer, Layer, Serializable, Serializable, (ScalarMatrix) ⇒ ScalarMatrix, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. ReconBasicLayer
  2. Reconstructable
  3. BasicLayer
  4. Layer
  5. Serializable
  6. Serializable
  7. Function1
  8. AnyRef
  9. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new ReconBasicLayer(IO: (Int, Int), act: Activation, w: ScalarMatrix = null, b: ScalarMatrix = null, rb: ScalarMatrix = null)

    IO

    is a pair of input & output, such as 2 -> 3

    act

    is an activation function to be applied

    w

    is initial weight matrix for the case that it is restored from JSON (default: null)

    b

    is inital bias matrix for the case that it is restored from JSON (default: null)

    rb

    is initial reconstruct bias matrix for the case that it is restored from JSON (default: null)

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. val W: IndexedSeq[ScalarMatrix]

    weights for update

    weights for update

    returns

    weights

    Definition Classes
    ReconBasicLayer → BasicLayer → Layer

  5. val act: Activation

    an activation function to be applied

    an activation function to be applied

    Attributes
    protected
    Definition Classes
    BasicLayer → Layer

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

    Definition Classes
    Function1
    Annotations
    @unspecialized()

  7. def apply(x: ScalarMatrix): ScalarMatrix

    Forward computation

    Forward computation

    x

    input matrix

    returns

    output matrix

    Definition Classes
    BasicLayer → Layer → Function1

  8. final def asInstanceOf[T0]: T0

    Definition Classes
    Any

  9. final val bias: ScalarMatrix

    Attributes
    protected
    Definition Classes
    BasicLayer

  10. def clone(): AnyRef

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

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

    Definition Classes
    Function1
    Annotations
    @unspecialized()

  12. val dW: IndexedSeq[ScalarMatrix]

    accumulated delta values

    accumulated delta values

    returns

    delta-weight

    Definition Classes
    ReconBasicLayer → BasicLayer → Layer

  13. final val dbias: ScalarMatrix

    Attributes
    protected
    Definition Classes
    BasicLayer

  14. def decodeBy_:(x: ScalarMatrix): ScalarMatrix

    Sugar: reconstruction

    Sugar: reconstruction

    x

    hidden layer output matrix

    returns

    tuple of reconstruction output

    Definition Classes
    ReconBasicLayer → Reconstructable

  15. def decodeUpdateBy(error: ScalarMatrix, input: ScalarMatrix, output: ScalarMatrix): ScalarMatrix

    Backpropagation of reconstruction.

    Backpropagation of reconstruction. For the information about backpropagation calculation, see kr.ac.kaist.ir.deep.layer.Layer

    error

    error matrix to be propagated

    input

    input of this layer

    output

    final reconstruction output of this layer

    returns

    propagated error

    Attributes
    protected[kr.ac.kaist.ir.deep]
    Definition Classes
    ReconBasicLayer → Reconstructable

  16. final val delta: ScalarMatrix

    Attributes
    protected
    Definition Classes
    BasicLayer

  17. final val drBias: ScalarMatrix

    Attributes
    protected

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

    Definition Classes
    AnyRef

  19. def equals(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any

  20. final val fanIn: Int

    Number of Fan-ins

    Number of Fan-ins

    Attributes
    protected
    Definition Classes
    BasicLayer

  21. final val fanOut: Int

    Number of output

    Number of output

    Attributes
    protected
    Definition Classes
    BasicLayer

  22. def finalize(): Unit

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

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

    Definition Classes
    AnyRef → Any

  24. def hashCode(): Int

    Definition Classes
    AnyRef → Any

  25. 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]
    Definition Classes
    Layer

  26. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any

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

    Definition Classes
    AnyRef

  28. final def notify(): Unit

    Definition Classes
    AnyRef

  29. final def notifyAll(): Unit

    Definition Classes
    AnyRef

  30. final val reBias: ScalarMatrix

    Attributes
    protected

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

    Definition Classes
    AnyRef

  32. 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

    Definition Classes
    ReconBasicLayer → BasicLayer → Layer

  33. def toString(): String

    Definition Classes
    Function1 → AnyRef → Any

  34. 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]
    Definition Classes
    BasicLayer → Layer
    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.

  35. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  38. final val weight: ScalarMatrix

    Attributes
    protected
    Definition Classes
    BasicLayer

Inherited from Reconstructable

Inherited from BasicLayer

Inherited from Layer

Inherited from Serializable

Inherited from Serializable

Inherited from (ScalarMatrix) ⇒ ScalarMatrix

Inherited from AnyRef

Inherited from Any

Ungrouped