BernoulliUnitLayer

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. def *(d: Double): MatrixParameterizedLayer

   Definition Classes

   MatrixParameterizedLayer → VectorSpace

5. def +(other: Layer): MatrixParameterizedLayer

   Definition Classes

   MatrixParameterizedLayer → VectorSpace

6. def -(other: Layer): MatrixParameterizedLayer

   Definition Classes

   MatrixParameterizedLayer → VectorSpace

7. def /(d: Double): MatrixParameterizedLayer

   Definition Classes

   MatrixParameterizedLayer → VectorSpace

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

   Definition Classes

   AnyRef

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

   Definition Classes

   Any

10. def activation(x: Double): Double

    Activation function of the neurons

    Activation function of the neurons

    Definition Classes

    UnscaledSigmoidUnitLayer → SigmoidUnitLayer → BiasedUnitLayer

11. def activation(ds: Mat): Mat

    Definition Classes

    BiasedUnitLayer

12. def activityColorscheme: (Double) ⇒ Int

    Color map for the activities

    Color map for the activities

    Definition Classes

    Layer

13. def activityShape: Option[(Int, Int)]

    Optionally, one can specify how to reshape the neuron activities for visualization (height, width).

    Optionally, one can specify how to reshape the neuron activities for visualization (height, width).

    Definition Classes

    Layer

14. final def asInstanceOf[T0]: T0

    Definition Classes

    Any

15. def build(biases: Mat): BernoulliUnitLayer

    Definition Classes

    BernoulliUnitLayer → UnscaledSigmoidUnitLayer → SigmoidUnitLayer → MatrixParameterizedLayer

16. var cachedInputPlusBias: Mat

    Attributes

    protected

    Definition Classes

    BiasedUnitLayer

17. def clone(): AnyRef

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

18. def copy: BernoulliUnitLayer

    Definition Classes

    BernoulliUnitLayer → RbmLayer

19. def derivative(x: Double): Double

    Calculates the derivative of the activation function

    Calculates the derivative of the activation function

    Definition Classes

    UnscaledSigmoidUnitLayer → SigmoidUnitLayer → BiasedUnitLayer

20. def derivative(ds: Mat): Mat

    Definition Classes

    BiasedUnitLayer

21. def dot(other: Layer): Double

    Definition Classes

    MatrixParameterizedLayer → VectorSpace

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

    Definition Classes

    AnyRef

23. def equals(arg0: Any): Boolean

    Definition Classes

    AnyRef → Any

24. def finalize(): Unit

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

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

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

    Definition Classes

    AnyRef → Any

26. def gradAndBackpropagationError(backpropagatedError: Mat): (MatrixParameterizedLayer, Mat)

    Calculates the gradient by pointwise multiplying the backpropagated error passed from above with the pointwise application of the derivative function to the cachedInputPlusBias, and summing the rows.

    Calculates the gradient by pointwise multiplying the backpropagated error passed from above with the pointwise application of the derivative function to the cachedInputPlusBias, and summing the rows. The matrix obtained before summing the rows is the new backpropagated error.

    backpropagatedError

    error propagated from above, formatted the same way (one row for each example) as input and output

    returns

    gradient (Layer-valued) and the next backpropagated error

    Definition Classes

    BiasedUnitLayer → Layer

27. def hashCode(): Int

    Definition Classes

    AnyRef → Any

28. val inputDimension: Int

    Definition Classes

    BiasedUnitLayer → Layer

29. def isInfinite: Boolean

    Definition Classes

    MatrixParameterizedLayer → VectorSpace

30. final def isInstanceOf[T0]: Boolean

    Definition Classes

    Any

31. def isInvalid: Boolean

    Definition Classes

    MatrixParameterizedLayer → VectorSpace

32. def isNaN: Boolean

    Definition Classes

    MatrixParameterizedLayer → VectorSpace

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

    Definition Classes

    AnyRef

34. def norm: Double

    Definition Classes

    VectorSpace

35. def normSq: Double

    Definition Classes

    VectorSpace

36. def normalized: Layer

    Definition Classes

    VectorSpace

37. final def notify(): Unit

    Definition Classes

    AnyRef

38. final def notifyAll(): Unit

    Definition Classes

    AnyRef

39. val outputDimension: Int

    Definition Classes

    BiasedUnitLayer → Layer

40. val parameters: Mat

    Definition Classes

    MatrixParameterizedLayer

41. def propagate(input: Mat): Mat

    Adds biases to each row of the input and applies the activation function pointwise.

    Adds biases to each row of the input and applies the activation function pointwise.

    Caches the input matrix with added biases in cachedInputPlusBias

    Definition Classes

    BiasedUnitLayer → Layer

42. def reinitialize(biasScaling: Double): RbmLayer

    Definition Classes

    BernoulliUnitLayer → RbmLayer

43. def reverseLayer: MatrixParameterizedLayer

    The reversal is trivial, just

    The reversal is trivial, just

    Definition Classes

    BiasedUnitLayer → Layer

44. def reversePropagate(output: Mat): Mat

    Does exactly the same as the propagate method.

    Does exactly the same as the propagate method.

    Definition Classes

    BiasedUnitLayer → Layer

45. def sample(activation: Double): Double

    Definition Classes

    BernoulliUnitLayer → RbmLayer

46. def sample(activation: Mat): Mat

    Definition Classes

    RbmLayer

47. val scalingFactor: Double

    Definition Classes

    SigmoidUnitLayer

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

    Definition Classes

    AnyRef

49. def toImage: BufferedImage

    Definition Classes

    RbmLayer → Visualizable

50. def toImage(w: Int, h: Int): BufferedImage

    Definition Classes

    Visualizable

51. def toImage(colormap: (Double) ⇒ Int): BufferedImage

    Definition Classes

    Visualizable

52. def toString(): String

    Definition Classes

    SigmoidUnitLayer → AnyRef → Any

53. def unary_-: MatrixParameterizedLayer

    Definition Classes

    MatrixParameterizedLayer → VectorSpace

54. def visualizeActivity(activity: Mat): BufferedImage

    Definition Classes

    Layer

55. final def wait(): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

58. def zero: MatrixParameterizedLayer

    Definition Classes

    MatrixParameterizedLayer → VectorSpace