PretrainLayer

Instance Constructors

new PretrainLayer()

Abstract Value Members

abstract def backward(delta: Vector[Double], acts: ActivationStack, model: Model): (Vector[Double], Weight, Bias)

Calculate the delta of this iteration.
Calculate the delta of this iteration. The input of the layer in forward phase can be restored from ActivationStack. It returns the delta of input layer of this layer and the delta of coefficient and intercept parameter.
returns
The delta tuple of the layer while back propagation. First is passed previous layer, the second and third is the delta of Weight and Bias parameter of the layer.

Definition Classes
Layer
abstract def createTmpLayer(): PretrainLayer

Returns the form for creating tmp model used while pretraining
abstract def decode(input: Vector[Double], model: Model, tmpModel: Model): (Vector[Double], Vector[Double])

Decode the value in hidden layer toward visible layer
Decode the value in hidden layer toward visible layer
returns
The value of visible layer

Attributes
protected
abstract def encode(input: Vector[Double], model: Model, tmpModel: Model): (Vector[Double], Vector[Double])

Encode the input toward hidden layer
Encode the input toward hidden layer
returns
The value of hidden layer

Attributes
protected
abstract def error(input: Vector[Double], visible: Vector[Double]): Vector[Double]

Attributes
protected
abstract def forward(acts: ActivationStack, model: Model): Vector[Double]

Calculate the output corresponding given input.
Calculate the output corresponding given input. Input is given as a top of ActivationStack.
returns
The output tuple of the layer.

Definition Classes
Layer
abstract val id: String

Definition Classes
Layer
abstract val inputSize: Int

Definition Classes
Layer
abstract val outputSize: Int

Definition Classes
Layer

Concrete Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def pretrain(acts: ActivationStack, model: Model, tmpModel: Model): ((Weight, Bias), (Weight, Bias), Double)

Pretraining with input data to the layer.
Pretraining with input data to the layer. We can assume AutoEncoder can inherit this class. It returns the gradient of weight and bias of the layer.
returns
(dWeight1, dBias1): Hidden Layer Gradient (dWeight2, dBias2): Visible Layer Gradient (Hidden Layer Gradient, Visible Layer Gradient)
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
Layer → AnyRef → Any
def validateParamShapes(weight: Matrix[Double], bias: Vector[Double]): Unit

Attributes
protected
Definition Classes
ShapeValidator
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Doc: package layer

abstract class PretrainLayer extends Layer with ShapeValidator

Instance Constructors

new PretrainLayer()

Abstract Value Members

abstract def backward(delta: Vector[Double], acts: ActivationStack, model: Model): (Vector[Double], Weight, Bias)

abstract def createTmpLayer(): PretrainLayer

abstract def decode(input: Vector[Double], model: Model, tmpModel: Model): (Vector[Double], Vector[Double])

abstract def encode(input: Vector[Double], model: Model, tmpModel: Model): (Vector[Double], Vector[Double])

abstract def error(input: Vector[Double], visible: Vector[Double]): Vector[Double]

abstract def forward(acts: ActivationStack, model: Model): Vector[Double]

abstract val id: String

abstract val inputSize: Int

abstract val outputSize: Int

Concrete Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def clone(): AnyRef

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 pretrain(acts: ActivationStack, model: Model, tmpModel: Model): ((Weight, Bias), (Weight, Bias), Double)

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

def toString(): String

def validateParamShapes(weight: Matrix[Double], bias: Vector[Double]): Unit

final def wait(): Unit

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

final def wait(arg0: Long): Unit

Inherited from ShapeValidator

Inherited from Layer

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped