Model

abstract def compile(lossFunction: LossFunction, optimizer: OptimizationAlgorithm, updater: Updater): Unit

Compile neural net architecture.

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def buildModelConfig(optimizer: OptimizationAlgorithm, updater: Updater, miniBatch: Boolean, biasInit: Double, seed: Long): Builder

Build model configuration from optimizer and seed.

def buildOutput(lossFunction: LossFunction): Unit

Make last layer of architecture an output layer using the provided loss function.

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def evaluate(dataset: DataSet, numClasses: Int): Evaluation

Evaluate model against an iterator over data set

def evaluate(dataset: DataSet): Evaluation

Evaluate model against an iterator over data set

def evaluate(iter: DataSetIterator, numClasses: Int): Evaluation

Evaluate model against an iterator over data set

def evaluate(iter: DataSetIterator): Evaluation

Evaluate model against an iterator over data set

def finalize(): Unit

def fit(dataset: DataSet, nbEpoch: Int, listeners: List[IterationListener]): Unit

Fit neural net to data.

def fit(iter: DataSetIterator, nbEpoch: Int, listeners: List[IterationListener]): Unit

Fit neural net to data.

final def getClass(): Class[_]

def getLayers: List[Node]

def getNetwork: MultiLayerNetwork

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

var layers: List[Node]

lazy val logger: Logger

var model: MultiLayerNetwork

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def predict(x: DataSet): INDArray

Use neural net to make prediction on input x.

def predict(x: INDArray): INDArray

Use neural net to make prediction on input x

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

def toJson: String

def toString(): String

def toYaml: String

final def wait(): Unit

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

final def wait(arg0: Long): Unit