Packages

case class MsraFiller(varianceNormAverage: Boolean = true) extends InitializationMethod with Product with Serializable

A Filler based on the paper [He, Zhang, Ren and Sun 2015]: Specifically accounts for ReLU nonlinearities.

Aside: for another perspective on the scaling factor, see the derivation of [Saxe, McClelland, and Ganguli 2013 (v3)].

It fills the incoming matrix by randomly sampling Gaussian data with std = sqrt(2 / n) where n is the fanIn, fanOut, or their average, depending on the varianceNormAverage parameter.

varianceNormAverage

VarianceNorm use average of (fanIn + fanOut) or just fanOut

Linear Supertypes
Serializable, Serializable, Product, Equals, InitializationMethod, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. MsraFiller
  2. Serializable
  3. Serializable
  4. Product
  5. Equals
  6. InitializationMethod
  7. AnyRef
  8. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new MsraFiller(varianceNormAverage: Boolean = true)

    varianceNormAverage

    VarianceNorm use average of (fanIn + fanOut) or just fanOut

Type Members

  1. type Shape = Array[Int]
    Definition Classes
    InitializationMethod

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 clone(): AnyRef
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @native() @throws( ... )
  6. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  7. def finalize(): Unit
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  8. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  9. def init[T](variable: Tensor[T], dataFormat: VariableFormat)(implicit ev: TensorNumeric[T]): Unit

    Initialize the given weight and bias.

    Initialize the given weight and bias.

    variable

    the weight to initialize

    dataFormat

    the data format of weight indicating the dimension order of the weight. "output_first" means output is in the lower dimension "input_first" means input is in the lower dimension.

    Definition Classes
    MsraFillerInitializationMethod
  10. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  11. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  12. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  13. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  14. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  15. val varianceNormAverage: Boolean
  16. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  17. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  18. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @throws( ... )

Inherited from Serializable

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from InitializationMethod

Inherited from AnyRef

Inherited from Any

Ungrouped