NeuralNetwork

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 activate(Z: DenseMatrix[Double], activation: String): DenseMatrix[Double]

   

   Performs the activation of a layer output

   Performs the activation of a layer output

   Z

   Instance vectors with neuron-transformed features

   activation

   Activation function identifier

   returns

   Activated layer output vector with same dimensions as Z

5. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

6. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

7. def derivActivate(A: DenseMatrix[Double], activation: String): DenseMatrix[Double]

   

   Calculates the derivative of the activation layer for their output for in backpropagation.

   Calculates the derivative of the activation layer for their output for in backpropagation.

   A

   Instance vectors with with activated features

   activation

   Activation function identifier

   returns

   Activated layer output vector with same dimensions as Z

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

   

   Definition Classes

   AnyRef

9. def equals(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

10. def feedForward(X: DenseMatrix[Double], W: IndexedSeq[DenseMatrix[Double]], b: IndexedSeq[DenseVector[Double]], activation: String): DenseMatrix[Double]

    

    Creates the neural network output by feeding all instances the network

    Creates the neural network output by feeding all instances the network

    X

    List of input instance feature vectors

    W

    Sequence of weight matrices of the layers

    b

    Sequence of intercept vectors of the layers

    activation

    Activation function identifier

    returns

    Output neuron values for each instance

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. def getDeltaClf(Z: DenseMatrix[Double], y: DenseVector[Int]): DenseMatrix[Double]

    

    Calculates the distance of the NN output to the truth for classification

    Calculates the distance of the NN output to the truth for classification

    Z

    List of instance network output vectors

    y

    List of instance labels

14. def getDeltaReg(Z: DenseMatrix[Double], y: DenseVector[Double]): DenseMatrix[Double]

    

    Calculates the distance of the NN output to the truth for regression

    Calculates the distance of the NN output to the truth for regression

    Z

    List of instance network output vectors

    y

    List of instance labels

15. def getLossClf(Z: DenseMatrix[Double], y: DenseVector[Int], W: IndexedSeq[DenseMatrix[Double]], regularization: Double): Double

    

    Calculates the classification loss of the predictions vs the truth

    Calculates the classification loss of the predictions vs the truth

    Z

    List of instance network output vectors

    y

    List of instance labels

    W

    Sequence of weight matrices of the layers

    regularization

    Regularization parameter

16. def getLossReg(Z: DenseMatrix[Double], y: DenseVector[Double], W: IndexedSeq[DenseMatrix[Double]], regularization: Double): Double

    

    Calculates the regression loss of the predictions vs the truth

    Calculates the regression loss of the predictions vs the truth

    Z

    List of instance network output vectors

    y

    List of instance labels

    W

    Sequence of weight matrices of the layers

    regularization

    Regularization parameter

17. def getProbabilities(Z: DenseMatrix[Double]): DenseMatrix[Double]

    

    Transforms the instance vectors in probability vectors

    Transforms the instance vectors in probability vectors

    Z

    List of instance network output vectors

    returns

    Vectors of probabilities to belong th each class

18. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

19. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

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

    

    Definition Classes

    AnyRef

21. def neuronTrafo(X: DenseMatrix[Double], W: DenseMatrix[Double], b: DenseVector[Double]): DenseMatrix[Double]

    

    Performs neuron transformation in one layer from n inputs to m outputs

    Performs neuron transformation in one layer from n inputs to m outputs

    X

    Instance vector with n features

    W

    Matrix of dimension n x m, n weights for m neurons

    b

    Vector with m entries, one intercept for each neuron

    returns

    Instance vector with m features

22. final def notify(): Unit

    

    Definition Classes

    AnyRef

23. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

24. def propagateBack(delta: DenseMatrix[Double], A: List[DenseMatrix[Double]], X: DenseMatrix[Double], W: IndexedSeq[DenseMatrix[Double]], b: IndexedSeq[DenseVector[Double]], activation: String, regularization: Double): List[(DenseMatrix[Double], DenseVector[Double])]

    

    Propagates the network outputs backward and saves necessary updates for weights and intercepts

    Propagates the network outputs backward and saves necessary updates for weights and intercepts

    delta

    List of output distances from truth for each output neuron for each instance

    A

    List of layer output vectors for all instances from forward propagation

    X

    List of input instance feature vectors

    W

    Sequence of weight matrices of the layers

    b

    Sequence of intercept vectors of the layers

    activation

    Activation function identifier

    regularization

    Regularization parameter

    returns

    List of updates for weight matrix and intercept vector

25. def propagateForward(X: DenseMatrix[Double], W: IndexedSeq[DenseMatrix[Double]], b: IndexedSeq[DenseVector[Double]], activation: String): List[DenseMatrix[Double]]

    

    Propagates the instances forward and saves the intermediate output

    Propagates the instances forward and saves the intermediate output

    X

    List of instance feature vectors

    W

    Sequence of weight matrices of the layers

    b

    Sequence of intercept vectors of the layers

    activation

    Activation function identifier

    returns

    List of layer output vectors for all instances

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

    

    Definition Classes

    AnyRef

27. def toString(): String

    

    Definition Classes

    AnyRef → Any

28. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )