c

epic.dense

BatchNormalizationTransform

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]])

Type Members

  1. case class Layer (bias: DenseVector[Double], size: Int, innerLayer: Transform.Layer) extends Transform.Layer[FV, DenseVector[Double]] with Product with Serializable

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. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  5. def clipHiddenWeightVectors(weights: DenseVector[Double], norm: Double, outputLayer: Boolean): Unit
    Definition Classes
    BatchNormalizationTransform → Transform
  6. def clone(): AnyRef
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  7. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  8. def extractLayer(dv: DenseVector[Double], forTrain: Boolean): Layer
    Definition Classes
    BatchNormalizationTransform → Transform
  9. def finalize(): Unit
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  10. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
  11. def getInterestingWeightIndicesForGradientCheck(offset: Int): Seq[Int]
    Definition Classes
    BatchNormalizationTransform → Transform
  12. val index: Index[Feature]
    Definition Classes
    BatchNormalizationTransform → Transform
  13. def initialWeightVector(initWeightsScale: Double, rng: Random, outputLayer: Boolean, spec: String): DenseVector[Double]
    Definition Classes
    BatchNormalizationTransform → Transform
  14. val inner: Transform[FV, DenseVector[Double]]
  15. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  16. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  17. final def notify(): Unit
    Definition Classes
    AnyRef
  18. final def notifyAll(): Unit
    Definition Classes
    AnyRef
  19. val size: Int
  20. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  21. val useBias: Boolean
  22. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  23. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  24. final def wait(arg0: Long): Unit
    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