Class

epic.dense

BatchNormalizationTransform

Related Doc: package dense

Permalink

case class BatchNormalizationTransform[FV](size: Int, useBias: Boolean, inner: Transform[FV, DenseVector[Double]]) extends Transform[FV, DenseVector[Double]] with Product with Serializable

Implements batch normalization from http://arxiv.org/pdf/1502.03167v3.pdf Basically, each unit is shifted and rescaled per minibatch so that its activations have mean 0 and variance 1. This has been demonstrated to help training deep networks, but doesn't seem to help here.

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

Instance Constructors

  1. new BatchNormalizationTransform(size: Int, useBias: Boolean, inner: Transform[FV, DenseVector[Double]])

    Permalink

Type Members

  1. case class Layer(bias: DenseVector[Double], size: Int, innerLayer: Transform.Layer) extends Transform.Layer[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
    BatchNormalizationTransform → Transform

  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): Layer

    Permalink
    Definition Classes
    BatchNormalizationTransform → Transform

  9. def finalize(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef → Any

  11. def getInterestingWeightIndicesForGradientCheck(offset: Int): Seq[Int]

    Permalink
    Definition Classes
    BatchNormalizationTransform → Transform

  12. val index: Index[Feature]

    Permalink
    Definition Classes
    BatchNormalizationTransform → Transform

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

    Permalink
    Definition Classes
    BatchNormalizationTransform → Transform

  14. val inner: Transform[FV, DenseVector[Double]]

    Permalink

  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. val size: Int

    Permalink

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

    Permalink
    Definition Classes
    AnyRef

  21. val useBias: Boolean

    Permalink

  22. final def wait(): Unit

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

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

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

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

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

Inherited from Product

Inherited from Equals

Inherited from Transform[FV, DenseVector[Double]]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped