Packages

trait Trainable[-Data, +Delta] extends AnyRef

A type class that makes result of forward as input of backward. To train a layer, a implement of Trainable has parameterized with types of the layer's Input and Output is required.

See also

This type class is required by train.

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Trainable
  2. AnyRef
  3. Any
Implicitly
  1. by toAnyLayerOps
  2. by any2stringadd
  3. by StringFormat
  4. by Ensuring
  5. by ArrowAssoc
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Abstract Value Members

  1. abstract def apply(data: Data): Delta

Concrete Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. def +(other: String): String
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to any2stringadd[Trainable[Data, Delta]] performed by method any2stringadd in scala.Predef.
    Definition Classes
    any2stringadd
  4. def ->[B](y: B): (Trainable[Data, Delta], B)
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to ArrowAssoc[Trainable[Data, Delta]] performed by method ArrowAssoc in scala.Predef.
    Definition Classes
    ArrowAssoc
    Annotations
    @inline()
  5. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  6. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  7. def clone(): AnyRef
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  8. def compose[NewInput <: Tape](g: Aux[NewInput, Input]): Aux[NewInput, Aux[OutputData, OutputDelta]]

    [use case]

    [use case]
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to AnyLayerOps[Input, OutputData, OutputDelta] performed by method toAnyLayerOps in com.thoughtworks.deeplearning.DifferentiableAny. This conversion will take place only if an implicit value of type Aux[Trainable[Data, Delta], Input, OutputData, OutputDelta] is in scope.
    Definition Classes
    AnyLayerOps
    Full Signature

    def compose[G, NewInput <: Tape, InputData, InputDelta](g: G)(implicit toLayer: Aux[G, NewInput, InputData, InputDelta], toInput: <:<[Aux[NewInput, Aux[InputData, InputDelta]], Aux[NewInput, Input]]): Aux[NewInput, Aux[OutputData, OutputDelta]]

    Example: 

    1. import com.thoughtworks.deeplearning.DifferentiableAny._
def composeNetwork(implicit thisLayer: INDArray @Symbolic)(anotherLayer: INDArray @Symbolic) = {
  thisLayer.compose(anotherLayer)
  9. def ensuring(cond: (Trainable[Data, Delta]) ⇒ Boolean, msg: ⇒ Any): Trainable[Data, Delta]
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to Ensuring[Trainable[Data, Delta]] performed by method Ensuring in scala.Predef.
    Definition Classes
    Ensuring
  10. def ensuring(cond: (Trainable[Data, Delta]) ⇒ Boolean): Trainable[Data, Delta]
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to Ensuring[Trainable[Data, Delta]] performed by method Ensuring in scala.Predef.
    Definition Classes
    Ensuring
  11. def ensuring(cond: Boolean, msg: ⇒ Any): Trainable[Data, Delta]
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to Ensuring[Trainable[Data, Delta]] performed by method Ensuring in scala.Predef.
    Definition Classes
    Ensuring
  12. def ensuring(cond: Boolean): Trainable[Data, Delta]
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to Ensuring[Trainable[Data, Delta]] performed by method Ensuring in scala.Predef.
    Definition Classes
    Ensuring
  13. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  14. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  15. def finalize(): Unit
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  16. def formatted(fmtstr: String): String
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to StringFormat[Trainable[Data, Delta]] performed by method StringFormat in scala.Predef.
    Definition Classes
    StringFormat
    Annotations
    @inline()
  17. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
  18. def hashCode(): Int
    Definition Classes
    AnyRef → Any
  19. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  20. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  21. final def notify(): Unit
    Definition Classes
    AnyRef
  22. final def notifyAll(): Unit
    Definition Classes
    AnyRef
  23. def predict[InputData, InputDelta](inputData: InputData)(implicit ev: <:<[Aux[Input, Aux[OutputData, OutputDelta]], Aux[Aux[InputData, InputDelta], Aux[OutputData, OutputDelta]]]): OutputData

    Returns the result of inputData's forward.

    Returns the result of inputData's forward.

    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to AnyLayerOps[Input, OutputData, OutputDelta] performed by method toAnyLayerOps in com.thoughtworks.deeplearning.DifferentiableAny. This conversion will take place only if an implicit value of type Aux[Trainable[Data, Delta], Input, OutputData, OutputDelta] is in scope.
    Definition Classes
    AnyLayerOps
    Example: 

    1. import com.thoughtworks.deeplearning.DifferentiableAny._
def composeNetwork(implicit inputData: INDArray @Symbolic) = ???
val predictor = composeNetwork
predictor.predict(testData)
  24. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  25. def toString(): String
    Definition Classes
    AnyRef → Any
  26. def train[InputData, InputDelta](inputData: InputData)(implicit ev: <:<[Aux[Input, Aux[OutputData, OutputDelta]], Aux[Aux[InputData, InputDelta], Aux[OutputData, OutputDelta]]], outputDataIsOutputDelta: Trainable[OutputData, OutputDelta]): OutputData

    Updates those weights embedded in anyLayer according to the result of inputData's backward.

    Updates those weights embedded in anyLayer according to the result of inputData's backward.

    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to AnyLayerOps[Input, OutputData, OutputDelta] performed by method toAnyLayerOps in com.thoughtworks.deeplearning.DifferentiableAny. This conversion will take place only if an implicit value of type Aux[Trainable[Data, Delta], Input, OutputData, OutputDelta] is in scope.
    Definition Classes
    AnyLayerOps
    Example: 

    1. import com.thoughtworks.deeplearning.DifferentiableAny._
def composeNetwork(implicit input: INDArray @Symbolic) = ???
val yourNetwork=composeNetwork
yourNetwork.train(testData)
  27. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  28. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  29. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  30. def withOutputDataHook(hook: (OutputData) ⇒ Unit): Aux[Input, Aux[OutputData, OutputDelta]]

    Returns a new Layer which is a wrapper of result of anyLayer's forward and will invoke hook(anyLayer.forward(input).value).

    Returns a new Layer which is a wrapper of result of anyLayer's forward and will invoke hook(anyLayer.forward(input).value). In DeepLearning.Scala, operation is not immediately run, but first filled the network with placeholders, until the entire network is running, the real data will replace placeholders. So if you want to know some layers's intermediate state, you need to use withOutputDataHook.

    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to AnyLayerOps[Input, OutputData, OutputDelta] performed by method toAnyLayerOps in com.thoughtworks.deeplearning.DifferentiableAny. This conversion will take place only if an implicit value of type Aux[Trainable[Data, Delta], Input, OutputData, OutputDelta] is in scope.
    Definition Classes
    AnyLayerOps
    Example: 

    1. import com.thoughtworks.deeplearning.DifferentiableAny._
(var:INDArray @Symbolic).withOutputDataHook{ data => println(data) }
  31. def →[B](y: B): (Trainable[Data, Delta], B)
    Implicit
    This member is added by an implicit conversion from Trainable[Data, Delta] to ArrowAssoc[Trainable[Data, Delta]] performed by method ArrowAssoc in scala.Predef.
    Definition Classes
    ArrowAssoc

Inherited from AnyRef

Inherited from Any

Inherited by implicit conversion toAnyLayerOps from Trainable[Data, Delta] to AnyLayerOps[Input, OutputData, OutputDelta]

Inherited by implicit conversion any2stringadd from Trainable[Data, Delta] to any2stringadd[Trainable[Data, Delta]]

Inherited by implicit conversion StringFormat from Trainable[Data, Delta] to StringFormat[Trainable[Data, Delta]]

Inherited by implicit conversion Ensuring from Trainable[Data, Delta] to Ensuring[Trainable[Data, Delta]]

Inherited by implicit conversion ArrowAssoc from Trainable[Data, Delta] to ArrowAssoc[Trainable[Data, Delta]]

Ungrouped