Class/Object

com.github.nearbydelta.deepspark.data

Weight

Related Docs: object Weight | package data

Permalink

class Weight[X <: Tensor[_, Double]] extends Serializable with KryoSerializable

Class for Weight object.

X

Either Matrix or DataVec

Linear Supertypes
KryoSerializable, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. Weight
  2. KryoSerializable
  3. Serializable
  4. Serializable
  5. AnyRef
  6. Any
  1. Hide All
  2. Show all
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Weight()

    Permalink

Value Members

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

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  3. def -=(seq: GenSeq[X])(implicit add: breeze.linalg.operators.OpAdd.InPlaceImpl2[X, X]): () ⇒ Unit

    Permalink

    Save data for update algorithm.

    Save data for update algorithm.

    seq

    Sequence of delta weights, per each instance.

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

    Permalink
    Definition Classes
    AnyRef → Any

  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. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  8. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  9. def finalize(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef → Any

  11. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  12. def isDefined: Boolean

    Permalink

    Check if the weight is successfully defined.

    Check if the weight is successfully defined.

    returns

    True if weight has value.

  13. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  14. def loss(implicit normImpl: breeze.linalg.norm.Impl[X, Double]): Double

    Permalink

    Compute weight loss

    Compute weight loss

    normImpl

    Norm implementation (implicit)

    returns

    Weight Loss (double).

  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. def read(kryo: Kryo, input: Input): Unit

    Permalink
    Definition Classes
    Weight → KryoSerializable

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

    Permalink
    Definition Classes
    AnyRef

  20. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  21. def value: X

    Permalink

    Value of this weight.

    Value of this weight.

    returns

    value of this weight.

  22. final def wait(): Unit

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

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

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

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

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

  25. def withUpdater(updater: Algorithm[X]): Weight[X]

    Permalink

    Set update algorithm for this weight.

    Set update algorithm for this weight.

    updater

    Update algorithm

    returns

    self.

  26. def withValue(x: X): Weight[X]

    Permalink

    Set value for this weight.

    Set value for this weight.

    x

    Value

    returns

    self.

  27. def write(kryo: Kryo, output: Output): Unit

    Permalink
    Definition Classes
    Weight → KryoSerializable

Inherited from KryoSerializable

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped