ml.combust.mleap.core.ann

LayerModel

trait LayerModel extends Serializable

Trait that holds Layer weights (or parameters). Implements functions needed for forward propagation, computing delta and gradient. Can return weights in Vector format.

Linear Supertypes
Serializable, Serializable, AnyRef, Any
Known Subclasses
AffineLayerModel, FunctionalLayerModel, SigmoidLayerModelWithSquaredError, SoftmaxLayerModelWithCrossEntropyLoss
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. LayerModel
  2. Serializable
  3. Serializable
  4. AnyRef
  5. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Abstract Value Members

  1. abstract def computePrevDelta(delta: DenseMatrix[Double], output: DenseMatrix[Double], prevDelta: DenseMatrix[Double]): Unit

    Computes the delta for back propagation.

    Computes the delta for back propagation. Delta is allocated based on the size provided by the LayerModel implementation and the stack (batch) size. Developer is responsible for checking the size of prevDelta when writing to it.

    delta

    delta of this layer

    output

    output of this layer

    prevDelta

    the previous delta (modified in place)

  2. abstract def eval(data: DenseMatrix[Double], output: DenseMatrix[Double]): Unit

    Evaluates the data (process the data through the layer).

    Evaluates the data (process the data through the layer). Output is allocated based on the size provided by the LayerModel implementation and the stack (batch) size. Developer is responsible for checking the size of output when writing to it.

    data

    data

    output

    output (modified in place)

  3. abstract def grad(delta: DenseMatrix[Double], input: DenseMatrix[Double], cumGrad: DenseVector[Double]): Unit

    Computes the gradient.

    Computes the gradient. cumGrad is a wrapper on the part of the weight vector. Size of cumGrad is based on weightSize provided by implementation of LayerModel.

    delta

    delta for this layer

    input

    input data

    cumGrad

    cumulative gradient (modified in place)

  4. abstract val weights: DenseVector[Double]

Concrete Value Members

  1. final def !=(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef

  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any

  3. final def ##(): Int

    Definition Classes
    AnyRef → Any

  4. final def ==(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef

  5. final def ==(arg0: Any): Boolean

    Definition Classes
    Any

  6. final def asInstanceOf[T0]: T0

    Definition Classes
    Any

  7. def clone(): AnyRef

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

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

    Definition Classes
    AnyRef

  9. def equals(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any

  10. def finalize(): Unit

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

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

    Definition Classes
    AnyRef → Any

  12. def hashCode(): Int

    Definition Classes
    AnyRef → Any

  13. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any

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

    Definition Classes
    AnyRef

  15. final def notify(): Unit

    Definition Classes
    AnyRef

  16. final def notifyAll(): Unit

    Definition Classes
    AnyRef

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

    Definition Classes
    AnyRef

  18. def toString(): String

    Definition Classes
    AnyRef → Any

  19. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped