Class

epic.dense

AffineOutputTransform

Related Doc: package dense

Permalink

case class AffineOutputTransform[FV](numOutputs: Int, numInputs: Int, innerTransform: Transform[FV, DenseVector[Double]], includeBias: Boolean = true) extends OutputTransform[FV, DenseVector[Double]] with Product with Serializable

Used at the output layer when we're only going to need some of the possible ouputs; it exposes the penultimate layer and then the Layer allows you to pass the results from that back in (caching it elsewhere) and only compute certain cells in the output layer (activationsFromPenultimateDot).

Linear Supertypes
Product, Equals, OutputTransform[FV, DenseVector[Double]], Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. AffineOutputTransform
  2. Product
  3. Equals
  4. OutputTransform
  5. Serializable
  6. Serializable
  7. AnyRef
  8. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new AffineOutputTransform(numOutputs: Int, numInputs: Int, innerTransform: Transform[FV, DenseVector[Double]], includeBias: Boolean = true)

    Permalink

Type Members

  1. case class OutputLayer(weights: DenseMatrix[Double], bias: DenseVector[Double], innerLayer: Layer) extends OutputTransform.OutputLayer[FV, DenseVector[Double]] with Product with Serializable

    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 clipHiddenWeightVectors(weights: DenseVector[Double], norm: Double, outputLayer: Boolean): Unit

    Permalink
    Definition Classes
    AffineOutputTransform → OutputTransform

  6. def clone(): AnyRef

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

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

    Permalink
    Definition Classes
    AnyRef

  8. def extractLayer(dv: DenseVector[Double], forTrain: Boolean): OutputLayer

    Permalink
    Definition Classes
    OutputTransform

  9. def extractLayerAndPenultimateLayer(weights: DenseVector[Double], forTrain: Boolean): (OutputLayer, Layer)

    Permalink
    Definition Classes
    AffineOutputTransform → OutputTransform

  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 getInterestingWeightIndicesForGradientCheck(offset: Int): Seq[Int]

    Permalink
    Definition Classes
    AffineOutputTransform → OutputTransform

  13. val includeBias: Boolean

    Permalink

  14. val index: SegmentedIndex[Feature, Index[Feature]]

    Permalink
    Definition Classes
    AffineOutputTransform → OutputTransform

  15. def initialWeightVector(initWeightsScale: Double, rng: Random, outputLayer: Boolean, spec: String): DenseVector[Double]

    Permalink

    N.B.

    N.B. Initialized to zero because this should *only* be used at the output layer, where zero initialization is appropriate

    Definition Classes
    AffineOutputTransform → OutputTransform

  16. val innerTransform: Transform[FV, DenseVector[Double]]

    Permalink

  17. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

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

    Permalink
    Definition Classes
    AnyRef

  19. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  20. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  21. val numInputs: Int

    Permalink

  22. val numOutputs: Int

    Permalink

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

    Permalink
    Definition Classes
    AnyRef

  24. final def wait(): Unit

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

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

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

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

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

Inherited from Product

Inherited from Equals

Inherited from OutputTransform[FV, DenseVector[Double]]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped