NeuralNet

abstract val g: Data

The training data

abstract def initParams(): Graph

abstract def learn(): Unit

Learn the parameters of the model.

abstract val numPoints: Int

abstract val optimizer: RegularizedOptimizer[Graph, Input, Output, Stream[(Input, Output)]]

abstract val params: Graph

abstract val transform: DataPipe[Data, Stream[(Input, Output)]]

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def _neuralStack: Graph

final def asInstanceOf[T0]: T0

def clone(): AnyRef

def data: Data

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def parameters(): Graph

Get the value of the parameters of the model.

def predict(point: Input): Output

Predict the value of the target variable given a point.

def setBatchFraction(f: Double): NeuralNet.this.type

def setLearningRate(alpha: Double): NeuralNet.this.type

def setMaxIterations(i: Int): NeuralNet.this.type

def setRegParam(r: Double): NeuralNet.this.type

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

def toString(): String

def updateParameters(param: Graph): Unit

final def wait(): Unit

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

final def wait(arg0: Long): Unit