BiasedUnitLayer

abstract def activation(d: Double): Double

Activation function of the neurons

abstract def build(newParameters: Mat): MatrixParameterizedLayer

abstract def derivative(d: Double): Double

Calculates the derivative of the activation function

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

def *(d: Double): MatrixParameterizedLayer

def +(other: Layer): MatrixParameterizedLayer

def -(other: Layer): MatrixParameterizedLayer

def /(d: Double): MatrixParameterizedLayer

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

def activation(ds: Mat): Mat

def activityColorscheme: (Double) ⇒ Int

Color map for the activities

def activityShape: Option[(Int, Int)]

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

final def asInstanceOf[T0]: T0

var cachedInputPlusBias: Mat

def clone(): AnyRef

def derivative(ds: Mat): Mat

def dot(other: Layer): Double

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

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.

def hashCode(): Int

val inputDimension: Int

def isInfinite: Boolean

final def isInstanceOf[T0]: Boolean

def isInvalid: Boolean

def isNaN: Boolean

final def ne(arg0: AnyRef): Boolean

def norm: Double

def normSq: Double

def normalized: Layer

final def notify(): Unit

final def notifyAll(): Unit

val outputDimension: Int

val parameters: Mat

def propagate(input: Mat): Mat

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

def reverseLayer: MatrixParameterizedLayer

The reversal is trivial, just

def reversePropagate(output: Mat): Mat

Does exactly the same as the propagate method.

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

def toImage: BufferedImage

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

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

def toString(): String

def unary_-: MatrixParameterizedLayer

def visualizeActivity(activity: Mat): BufferedImage

final def wait(): Unit

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

final def wait(arg0: Long): Unit

def zero: MatrixParameterizedLayer