Packages

  • package root
    Definition Classes
    root
  • package com
    Definition Classes
    root
  • package thoughtworks
    Definition Classes
    com
  • package deeplearning

    This is the documentation for the DeepLearning.Scala

    This is the documentation for the DeepLearning.Scala

    Overview

    BufferedLayer, DifferentiableAny, DifferentiableNothing, Layer, Poly and Symbolic are base packages which contains necessary operations , all other packages dependent on those base packages.

    If you want to implement a layer, you need to know how to use base packages.

    Imports guidelines

    If you want use some operations of Type T, you should import:

    import com.thoughtworks.deeplearning.DifferentiableT._

    it means: If you want use some operations of INDArray, you should import:

    import com.thoughtworks.deeplearning.DifferentiableINDArray._

    If you write something like this:

    def softmax(implicit scores: INDArray @Symbolic): INDArray @Symbolic = {
  val expScores = exp(scores)
  expScores / expScores.sum(1)
}

    If compiler shows error :

    Could not infer implicit value for com.thoughtworks.deeplearning.Symbolic[org.nd4j.linalg.api.ndarray.INDArray]

    you need add import this time :

    import com.thoughtworks.deeplearning.DifferentiableINDArray._

    If you write something like this:

    def crossEntropyLossFunction(
  implicit pair: (INDArray :: INDArray :: HNil) @Symbolic)
: Double @Symbolic = {
 val score = pair.head
 val label = pair.tail.head
 -(label * log(score * 0.9 + 0.1) + (1.0 - label) * log(1.0 - score * 0.9)).mean
}

    If the compiler shows error:

    value * is not a member of com.thoughtworks.deeplearning.Layer.Aux[com.thoughtworks.deeplearning.Layer.Tape.Aux[org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray],com.thoughtworks.deeplearning.DifferentiableINDArray.INDArrayPlaceholder.Tape]val bias = Nd4j.ones(numberOfOutputKernels).toWeight * 0.1...

    you need add import :

    import com.thoughtworks.deeplearning.Poly.MathMethods.*
import com.thoughtworks.deeplearning.DifferentiableINDArray._

    If the compiler shows error:

    not found: value log -(label * log(score * 0.9 + 0.1) + (1.0 - label) * log(1.0 - score * 0.9)).mean...

    you need add import:

    import com.thoughtworks.deeplearning.Poly.MathFunctions.*
import com.thoughtworks.deeplearning.DifferentiableINDArray._

    Those + - * / and log exp abs max min are defined at MathMethods and MathFunctions，those method are been implemented at DifferentiableType，so you need to import the implicit of DifferentiableType.

    Composability

    Neural networks created by DeepLearning.scala are composable. You can create large networks by combining smaller networks. If two larger networks share some sub-networks, the weights in shared sub-networks trained with one network affect the other network.

    Definition Classes
    thoughtworks
    See also

    Compose

  • object DifferentiableInt

    A namespace of common operators for Int layers.

    A namespace of common operators for Int layers.

    Author:

    杨博 (Yang Bo) <[email protected]>

    Definition Classes
    deeplearning
  • object Layers
    Definition Classes
    DifferentiableInt
  • Negative
  • Plus
  • Reciprocal
  • Substract
  • Times
  • Weight

final case class Weight(value: Int)(implicit optimizer: Optimizer) extends Layer with IntMonoidTape with Product with Serializable

Linear Supertypes
Serializable, Serializable, Product, Equals, IntMonoidTape, Tape, AutoCloseable, Layer, AnyRef, Any
Type Hierarchy
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Weight
  2. Serializable
  3. Serializable
  4. Product
  5. Equals
  6. IntMonoidTape
  7. Tape
  8. AutoCloseable
  9. Layer
  10. AnyRef
  11. Any
Implicitly
  1. by any2stringadd
  2. by StringFormat
  3. by Ensuring
  4. by ArrowAssoc
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Weight(value: Int)(implicit optimizer: Optimizer)

Type Members

  1. type Data = Int

    Type of the result of forward pass.

    Type of the result of forward pass.

    Definition Classes
    IntMonoidTape → Tape
    See also

    value

  2. type Delta = Float

    Type of the information passing in backward pass, usually the partial derivative of Data.

    Type of the information passing in backward pass, usually the partial derivative of Data.

    Definition Classes
    IntMonoidTape → Tape
    See also

    backward

  3. type Input = Tape
    Definition Classes
    Weight → Layer
  4. type Output = Tape { ... /* 2 definitions in type refinement */ }
    Definition Classes
    Weight → Layer

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 Weight to any2stringadd[Weight] performed by method any2stringadd in scala.Predef.
    Definition Classes
    any2stringadd
  4. def ->[B](y: B): (Weight, B)
    Implicit
    This member is added by an implicit conversion from Weight to ArrowAssoc[Weight] 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. final def backward(delta: ⇒ Delta): Unit

    invoke forceBackward if isTrainable is true

    invoke forceBackward if isTrainable is true

    Definition Classes
    Tape
    Annotations
    @inline()
    See also

    Delta

  8. def clone(): AnyRef
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  9. def close(): Unit
    Definition Classes
    Weight → AutoCloseable
  10. def duplicate(): Weight

    Returns a new Tape that shares the same value and backward behavior with this Tape.

    Returns a new Tape that shares the same value and backward behavior with this Tape.

    Definition Classes
    Weight → Tape
    Note

    The newly created Tape and this Tape must be closed independently.

  11. def ensuring(cond: (Weight) ⇒ Boolean, msg: ⇒ Any): Weight
    Implicit
    This member is added by an implicit conversion from Weight to Ensuring[Weight] performed by method Ensuring in scala.Predef.
    Definition Classes
    Ensuring
  12. def ensuring(cond: (Weight) ⇒ Boolean): Weight
    Implicit
    This member is added by an implicit conversion from Weight to Ensuring[Weight] performed by method Ensuring in scala.Predef.
    Definition Classes
    Ensuring
  13. def ensuring(cond: Boolean, msg: ⇒ Any): Weight
    Implicit
    This member is added by an implicit conversion from Weight to Ensuring[Weight] performed by method Ensuring in scala.Predef.
    Definition Classes
    Ensuring
  14. def ensuring(cond: Boolean): Weight
    Implicit
    This member is added by an implicit conversion from Weight to Ensuring[Weight] performed by method Ensuring in scala.Predef.
    Definition Classes
    Ensuring
  15. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  16. def finalize(): Unit
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  17. def forceBackward(delta: Delta): Unit
    Attributes
    protected
    Definition Classes
    Weight → Tape
  18. def formatted(fmtstr: String): String
    Implicit
    This member is added by an implicit conversion from Weight to StringFormat[Weight] performed by method StringFormat in scala.Predef.
    Definition Classes
    StringFormat
    Annotations
    @inline()
  19. def forward(any: Input): Weight
    Definition Classes
    Weight → Layer
  20. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
  21. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  22. def isTrainable: Boolean
    Definition Classes
    Weight → Tape
  23. final def monoid: Monoid[Delta]
    Attributes
    protected
    Definition Classes
    IntMonoidTape
  24. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  25. final def notify(): Unit
    Definition Classes
    AnyRef
  26. final def notifyAll(): Unit
    Definition Classes
    AnyRef
  27. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  28. var value: Int
    Definition Classes
    Weight → Tape
  29. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  30. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  31. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  32. def →[B](y: B): (Weight, B)
    Implicit
    This member is added by an implicit conversion from Weight to ArrowAssoc[Weight] performed by method ArrowAssoc in scala.Predef.
    Definition Classes
    ArrowAssoc

Inherited from Serializable

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from IntMonoidTape

Inherited from Tape

Inherited from AutoCloseable

Inherited from Layer

Inherited from AnyRef

Inherited from Any

Inherited by implicit conversion any2stringadd from Weight to any2stringadd[Weight]

Inherited by implicit conversion StringFormat from Weight to StringFormat[Weight]

Inherited by implicit conversion Ensuring from Weight to Ensuring[Weight]

Inherited by implicit conversion ArrowAssoc from Weight to ArrowAssoc[Weight]

Ungrouped