Object

com.github.nearbydelta.deepspark.data

ManhattanErr

Related Doc: package data

Permalink

object ManhattanErr extends Objective

Objective Function: Sum of Absolute Error

Example: 

  1. val output = net(input)
            val err = ManhattanErr(real, output)
            val diff = ManhattanErr.derivative(real, output)
Note

In mathematics, L1-distance is called Manhattan distance.

Linear Supertypes
Objective, Serializable, Serializable, (DataVec, DataVec) ⇒ Double, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. ManhattanErr
  2. Objective
  3. Serializable
  4. Serializable
  5. Function2
  6. AnyRef
  7. Any
  1. Hide All
  2. Show all
Visibility
  1. Public
  2. All

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. def apply(real: DataVec, output: DataVec): Double

    Permalink

    Compute error (loss)

    Compute error (loss)

    real

    the expected real output

    output

    the computed output of the network

    returns

    the error

    Definition Classes
    ManhattanErr → Objective → Function2

  5. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  6. def clone(): AnyRef

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

  7. def curried: (DataVec) ⇒ (DataVec) ⇒ Double

    Permalink
    Definition Classes
    Function2
    Annotations
    @unspecialized()

  8. def derivative(real: DataVec, output: DataVec): DataVec

    Permalink

    Compute differentiation value of this objective function at x = r - o

    Compute differentiation value of this objective function at x = r - o

    real

    the expected real output, r

    output

    the computed output of the network, o

    returns

    differentiation value at f(x)=fx, which is a column vector

    Definition Classes
    ManhattanErr → Objective

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

    Permalink
    Definition Classes
    AnyRef

  10. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  11. def finalize(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef → Any

  13. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  14. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

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

    Permalink
    Definition Classes
    AnyRef

  16. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  17. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

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

    Permalink
    Definition Classes
    AnyRef

  19. def toString(): String

    Permalink
    Definition Classes
    Function2 → AnyRef → Any

  20. def tupled: ((DataVec, DataVec)) ⇒ Double

    Permalink
    Definition Classes
    Function2
    Annotations
    @unspecialized()

  21. final def wait(): Unit

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

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

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

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

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

Inherited from Objective

Inherited from Serializable

Inherited from Serializable

Inherited from (DataVec, DataVec) ⇒ Double

Inherited from AnyRef

Inherited from Any

Ungrouped