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
Ordering
- Alphabetic
- By Inheritance
Inherited
- AffineOutputTransform
- Product
- Equals
- OutputTransform
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- All
Instance Constructors
Type Members
- case class OutputLayer (weights: DenseMatrix[Double], bias: DenseVector[Double], innerLayer: Layer) extends OutputTransform.OutputLayer[FV, DenseVector[Double]] with Product with Serializable
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clipHiddenWeightVectors(weights: DenseVector[Double], norm: Double, outputLayer: Boolean): Unit
- Definition Classes
- AffineOutputTransform → OutputTransform
-
def
clone(): AnyRef
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
extractLayer(dv: DenseVector[Double], forTrain: Boolean): OutputLayer
- Definition Classes
- OutputTransform
-
def
extractLayerAndPenultimateLayer(weights: DenseVector[Double], forTrain: Boolean): (OutputLayer, Layer)
- Definition Classes
- AffineOutputTransform → OutputTransform
-
def
finalize(): Unit
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
-
def
getInterestingWeightIndicesForGradientCheck(offset: Int): Seq[Int]
- Definition Classes
- AffineOutputTransform → OutputTransform
- val includeBias: Boolean
-
val
index: SegmentedIndex[Feature, Index[Feature]]
- Definition Classes
- AffineOutputTransform → OutputTransform
-
def
initialWeightVector(initWeightsScale: Double, rng: Random, outputLayer: Boolean, spec: String): DenseVector[Double]
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
- val innerTransform: Transform[FV, DenseVector[Double]]
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- val numInputs: Int
- val numOutputs: Int
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )