Trait

com.github.nearbydelta.deepspark.word.layer

FixedLedger

Related Doc: package layer

Permalink

trait FixedLedger[OutInfo] extends InputLayer[Array[Int], OutInfo]

Layer: Basic, Fully-connected Layer

Linear Supertypes
InputLayer[Array[Int], OutInfo], Layer[Array[Int], OutInfo], KryoSerializable, Serializable, Serializable, AnyRef, Any
Known Subclasses
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. FixedLedger
  2. InputLayer
  3. Layer
  4. KryoSerializable
  5. Serializable
  6. Serializable
  7. AnyRef
  8. Any
  1. Hide All
  2. Show all
Visibility
  1. Public
  2. All

Abstract Value Members

  1. abstract def apply(in: Array[Int]): OutInfo

    Permalink

    Apply this layer (forward computation)

    Apply this layer (forward computation)

    in

    Input value

    returns

    Output computation information.

    Definition Classes
    Layer
  2. abstract val outVecOf: (OutInfo) ⇒ DataVec

    Permalink

    Output converter from OutInfo to Vector *

    Output converter from OutInfo to Vector *

    Definition Classes
    Layer

Concrete 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. var NIn: Int

    Permalink

    Size of input *

    Size of input *

    Definition Classes
    Layer
  5. var NOut: Int

    Permalink

    Size of output *

    Size of output *

    Definition Classes
    Layer
  6. def apply(in: RDD[(Long, Array[Int])]): RDD[(Long, DataVec)]

    Permalink

    Apply RDD of vector.

    Apply RDD of vector.

    in

    RDD of (ID, Value), ID is Long value.

    returns

    RDD of (ID, Vector), with same ID for input.

    Definition Classes
    Layer
  7. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  8. def backprop(seq: ParSeq[((Array[Int], OutInfo), DataVec)]): (ParSeq[DataVec], ParSeq[() ⇒ Unit])

    Permalink

    Backward computation

    Backward computation

    seq

    Sequence of entries to be used for backward computation.

    returns

    Error sequence, to backpropagate into previous layer.

    Definition Classes
    FixedLedgerLayer
    Note

    For the computation, we only used denominator layout. (cf. Wikipedia Page of Matrix Computation) For the computation rules, see "Matrix Cookbook" from MIT.

  9. def backward(error: ParSeq[DataVec]): (ParSeq[DataVec], ParSeq[() ⇒ Unit])

    Permalink

    Backward computation using propagated error.

    Backward computation using propagated error.

    error

    Propagated error sequence.

    returns

    Error sequence for back propagation.

    Definition Classes
    Layer
  10. var bcModel: Broadcast[LedgerModel]

    Permalink
  11. def broadcast(sc: SparkContext): Unit

    Permalink

    Broadcast resources of this layer.

    Broadcast resources of this layer.

    sc

    Spark Context

    Definition Classes
    FixedLedgerInputLayer
  12. def clone(): AnyRef

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

    Permalink
    Definition Classes
    AnyRef
  14. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  15. implicit val evidenceI: ClassTag[Array[Int]]

    Permalink

    ClassTag for input *

    ClassTag for input *

    Attributes
    protected
    Definition Classes
    FixedLedgerLayer
  16. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  17. def forward(in: ParSeq[Array[Int]]): ParSeq[DataVec]

    Permalink

    Apply Parallel Sequence of vector.

    Apply Parallel Sequence of vector.

    in

    Parallel Sequence of Input

    returns

    Parallel Sequence of Vector

    Definition Classes
    Layer
  18. final def forward(in: RDD[(Long, Array[Int])]): RDD[(Long, DataVec)]

    Permalink

    Apply RDD of vector.

    Apply RDD of vector.

    in

    RDD of (ID, Value), ID is Long value.

    returns

    RDD of (ID, Vector), with same ID for input.

    Definition Classes
    Layer
  19. final def forward(in: Array[Int]): DataVec

    Permalink

    Apply this layer (forward computation)

    Apply this layer (forward computation)

    in

    Input value

    returns

    Output Vector

    Definition Classes
    Layer
  20. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  21. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  22. def initiateBy(builder: WeightBuilder): FixedLedger.this.type

    Permalink

    Set weight builder for this layer.

    Set weight builder for this layer.

    builder

    Weight builder to be applied

    returns

    self

    Definition Classes
    Layer
  23. var inoutSEQ: ParSeq[(Array[Int], OutInfo)]

    Permalink

    Sequence for backpropagation.

    Sequence for backpropagation. Stores output values. *

    Attributes
    protected
    Definition Classes
    Layer
  24. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  25. var isUpdatable: Boolean

    Permalink

    True if this layer affected by backward propagation *

    True if this layer affected by backward propagation *

    Attributes
    protected
    Definition Classes
    Layer
  26. def loss: Double

    Permalink

    Weight Loss of this layer

    Weight Loss of this layer

    returns

    Weight loss

    Definition Classes
    FixedLedgerLayer
  27. var model: LedgerModel

    Permalink
  28. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  29. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  30. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  31. def pad: DataVec

    Permalink
    Attributes
    protected
  32. var padID: Int

    Permalink
    Attributes
    protected
  33. def read(kryo: Kryo, input: Input): Unit

    Permalink
    Definition Classes
    FixedLedgerLayer → KryoSerializable
  34. def setUpdatable(bool: Boolean): Unit

    Permalink

    Assign whether this layer updatable or not.

    Assign whether this layer updatable or not. value.

    bool

    True if this layer used in backpropagation.

    Definition Classes
    Layer
  35. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  36. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any
  37. def unbroadcast(): Unit

    Permalink

    Unpersist broadcast of this layer.

    Unpersist broadcast of this layer.

    Definition Classes
    FixedLedgerInputLayer
  38. def vectorOf(str: Int): DataVec

    Permalink
    Attributes
    protected
  39. final def wait(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  42. def withModel(model: LedgerModel): FixedLedger.this.type

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

    Permalink
    Definition Classes
    FixedLedgerLayer → KryoSerializable

Deprecated Value Members

  1. def withInput(in: Int): FixedLedger.this.type

    Permalink

    Set input size

    Set input size

    in

    Size of input

    returns

    self

    Definition Classes
    FixedLedgerLayer
    Annotations
    @deprecated
    Deprecated
  2. def withOutput(out: Int): FixedLedger.this.type

    Permalink

    Set output size

    Set output size

    out

    Size of output

    returns

    self

    Definition Classes
    FixedLedgerLayer
    Annotations
    @deprecated
    Deprecated

Inherited from InputLayer[Array[Int], OutInfo]

Inherited from Layer[Array[Int], OutInfo]

Inherited from KryoSerializable

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped