L1Regularizer

Instance Constructors

new L1Regularizer(l1: Double)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

l1
l1 regularization rate

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
def accRegularization(parameter: Tensor[T], gradParameter: Tensor[T], scale: Double): Unit

The method need to be override by the concrete regularizer class It accumulates the gradient of the regularization of parameter to gradParameter
The method need to be override by the concrete regularizer class It accumulates the gradient of the regularization of parameter to gradParameter
parameter
the parameter that is regularized
gradParameter
the gradient of the parameter
scale
the scale of gradParameters

Definition Classes
L1L2Regularizer → Regularizer
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def disable(): Unit

Disable the regularization feature
Disable the regularization feature

Definition Classes
Regularizer
def enable(): Unit

Enable the regularization feature
Enable the regularization feature

Definition Classes
Regularizer
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def finalize(): Unit

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

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

Definition Classes
Any
val l1: Double

l1 regularization rate
l1 regularization rate

Definition Classes
L1Regularizer → L1L2Regularizer
val l2: Double

l2 regularization rate
l2 regularization rate

Definition Classes
L1L2Regularizer
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def preCheck(parameter: Tensor[T], gradParameter: Tensor[T]): Boolean

Check the regularization is applied or not
Check the regularization is applied or not
parameter
the parameter that is regularized
gradParameter
the gradient of the parameter
returns
a boolean, if true, accumulates the gradient of regularization, otherwise not.

Attributes
protected
Definition Classes
Regularizer
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
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 optim

case class L1Regularizer[T](l1: Double)(implicit evidence$3: ClassTag[T], ev: TensorNumeric[T]) extends L1L2Regularizer[T] with Product with Serializable

Instance Constructors

new L1Regularizer(l1: Double)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def accRegularization(parameter: Tensor[T], gradParameter: Tensor[T], scale: Double): Unit

final def asInstanceOf[T0]: T0

def clone(): AnyRef

def disable(): Unit

def enable(): Unit

final def eq(arg0: AnyRef): Boolean

def finalize(): Unit

final def getClass(): Class[_]

final def isInstanceOf[T0]: Boolean

val l1: Double

val l2: Double

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def preCheck(parameter: Tensor[T], gradParameter: Tensor[T]): Boolean

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

final def wait(): Unit

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

final def wait(arg0: Long): Unit

Inherited from Product

Inherited from Equals

Inherited from L1L2Regularizer[T]

Inherited from Regularizer[T]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped