FFBackProp

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. def _momentum: Double

   

   Definition Classes

   GradBasedBackPropagation

5. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

6. val backPropagate: MetaPipe[(DenseMatrix[Double], DenseVector[Double]), Stream[(PatternType, PatternType)], Stream[DenseVector[Double]]]

   

   A meta pipeline which for a particular value of the layer parameters, returns a data pipe which takes as input Stream of Tuple2 consisting of delta's and gradients of activation function with respect to their local fields (calculated via Activation.grad).

   A meta pipeline which for a particular value of the layer parameters, returns a data pipe which takes as input Stream of Tuple2 consisting of delta's and gradients of activation function with respect to their local fields (calculated via Activation.grad).

   Definition Classes

   FFBackProp → GradBasedBackPropagation

7. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

8. val computeOutputDelta: StreamMapPipe[(PatternType, PatternType, PatternType), (DenseVector[Double], Double)]

   

   A data pipeline which takes Tuple3 consisting of output layer activations, targets and gradients of output activations with respect to their local fields, respectively and returns the output layer delta values.

   A data pipeline which takes Tuple3 consisting of output layer activations, targets and gradients of output activations with respect to their local fields, respectively and returns the output layer delta values.

   Definition Classes

   FFBackProp → GradBasedBackPropagation

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

   

   Definition Classes

   AnyRef

10. def equals(arg0: Any): Boolean

    

    Definition Classes

    AnyRef → Any

11. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

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

    

    Definition Classes

    AnyRef → Any

13. val gradCompute: DataPipe[Stream[(PatternType, PatternType)], (DenseMatrix[Double], DenseVector[Double])]

    

    A data pipeline which takes as input a Stream of Tuple2 whose first element is the activation and second element the delta value and outputs the gradient of the layer parameters.

    A data pipeline which takes as input a Stream of Tuple2 whose first element is the activation and second element the delta value and outputs the gradient of the layer parameters.

    Definition Classes

    FFBackProp → GradBasedBackPropagation

14. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

15. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

16. var miniBatchFraction: Double

    

    Attributes

    protected

    Definition Classes

    RegularizedOptimizer

17. var momentum: Double

    

    Attributes

    protected

    Definition Classes

    GradBasedBackPropagation

18. def momentum_(m: Double): GradBasedBackPropagation[(DenseMatrix[Double], DenseVector[Double]), DenseVector[Double]]

    

    Definition Classes

    GradBasedBackPropagation

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

    

    Definition Classes

    AnyRef

20. final def notify(): Unit

    

    Definition Classes

    AnyRef

21. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

22. var numIterations: Int

    

    Attributes

    protected

    Definition Classes

    RegularizedOptimizer

23. def optimize(nPoints: Long, data: Stream[(DenseVector[Double], DenseVector[Double])], initialStack: NeuralStack[(DenseMatrix[Double], DenseVector[Double]), DenseVector[Double]]): NeuralStack[(DenseMatrix[Double], DenseVector[Double]), DenseVector[Double]]

    

    Solve the optimization problem of determining NeuralStack weights, from training data.

    Solve the optimization problem of determining NeuralStack weights, from training data.

    nPoints

    The number of training data points

    data

    Training data

    initialStack

    The initial NeuralStack before training

    returns

    A NeuralStack with the learned layer weights and biases.

    Definition Classes

    GradBasedBackPropagation → Optimizer

24. var regParam: Double

    

    Attributes

    protected

    Definition Classes

    RegularizedOptimizer

25. def setMiniBatchFraction(fraction: Double): FFBackProp.this.type

    

    Set fraction of data to be used for each SGD iteration.

    Set fraction of data to be used for each SGD iteration. Default 1.0 (corresponding to deterministic/classical gradient descent)

    Definition Classes

    RegularizedOptimizer

26. def setNumIterations(iters: Int): FFBackProp.this.type

    

    Set the number of iterations for SGD.

    Set the number of iterations for SGD. Default 100.

    Definition Classes

    RegularizedOptimizer

27. def setRegParam(regParam: Double): FFBackProp.this.type

    

    Set the regularization parameter.

    Set the regularization parameter. Default 0.0.

    Definition Classes

    RegularizedOptimizer

28. def setStepSize(step: Double): FFBackProp.this.type

    

    Set the initial step size of SGD for the first step.

    Set the initial step size of SGD for the first step. Default 1.0. In subsequent steps, the step size will decrease with stepSize/sqrt(t)

    Definition Classes

    RegularizedOptimizer

29. val stackFactory: NeuralStackFactory[(DenseMatrix[Double], DenseVector[Double]), DenseVector[Double]]

    

    Definition Classes

    FFBackProp → GradBasedBackPropagation

30. var stepSize: Double

    

    Attributes

    protected

    Definition Classes

    RegularizedOptimizer

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

    

    Definition Classes

    AnyRef

32. def toString(): String

    

    Definition Classes

    AnyRef → Any

33. val updater: FFLayerUpdater

    

    Performs the actual update to the layer parameters after all the gradients have been calculated.

    Performs the actual update to the layer parameters after all the gradients have been calculated.

    Definition Classes

    FFBackProp → GradBasedBackPropagation

34. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )