Class

com.github.rzykov.fastml4j.loss

LogisticLoss

Related Doc: package loss

Permalink

class LogisticLoss extends Loss

Created by rzykov on 31/05/17.

Linear Supertypes
Loss, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. LogisticLoss
  2. Loss
  3. AnyRef
  4. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new LogisticLoss()

    Permalink

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  3. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  4. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  5. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  6. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  7. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  8. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  9. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any

  10. def gradient(weights: INDArray, dataSet: DataSet): INDArray

    Permalink

    Calculates the gradient of loss function value

    Calculates the gradient of loss function value

    weights

    input weights vector

    dataSet

    input weights vector

    returns

    computed value of the gradient of the loss function

    Definition Classes
    LogisticLoss → Loss

  11. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  12. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  13. def loss(weights: INDArray, dataSet: DataSet): Float

    Permalink

    Calculates the loss function value

    Calculates the loss function value

    weights

    input weights vector

    dataSet

    training dataset

    returns

    computed value of the loss function

    Definition Classes
    LogisticLoss → Loss

  14. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  15. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  16. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  17. def numericGradient(weights: INDArray, dataSet: DataSet, eps: Float = 1e-6f): INDArray

    Permalink

    Calculate the gradient numerically, useful for a testing of gradient functions More about gradient checking: http://cs231n.github.io/neural-networks-3/

    Calculate the gradient numerically, useful for a testing of gradient functions More about gradient checking: http://cs231n.github.io/neural-networks-3/

    weights

    input weights vector

    dataSet

    input weights vector

    eps

    delta parameter for a derivative calculation

    returns

    computed value of the gradient of the loss function

    Definition Classes
    Loss

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

    Permalink
    Definition Classes
    AnyRef

  19. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  20. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  22. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from Loss

Inherited from AnyRef

Inherited from Any

Ungrouped