kr.ac.kaist.ir.deep.train

RAEType

class RAEType extends TreeType

Input Operation : VectorTree as Input & Recursive Auto-Encoder Training (no output type)

Example: 

  1. var make = new RAEType(error = CrossEntropyErr)
           var corruptedIn = make corrupted in
           var out = make onewayTrip (net, corruptedIn)
Note

This implementation designed as a replica of the traditional RAE in this paper

,

We recommend that you should not apply this method to non-AutoEncoder tasks

Linear Supertypes
TreeType, ManipulationType[BinaryTree, Null], Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. RAEType
  2. TreeType
  3. ManipulationType
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new RAEType(corrupt: Corruption = NoCorruption, error: Objective = SquaredErr)

    corrupt

    Corruption that supervises how to corrupt the input matrix. (Default : kr.ac.kaist.ir.deep.train.NoCorruption)

    error

    An objective function (Default: kr.ac.kaist.ir.deep.fn.SquaredErr)

Value Members

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

    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Definition Classes
    AnyRef → Any

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

    Definition Classes
    AnyRef → Any

  4. final def asInstanceOf[T0]: T0

    Definition Classes
    Any

  5. def clone(): AnyRef

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

  6. val corrupt: Corruption

    Corruption that supervises how to corrupt the input matrix.

    Corruption that supervises how to corrupt the input matrix. (Default : kr.ac.kaist.ir.deep.train.NoCorruption)

    Definition Classes
    RAEType → ManipulationType

  7. def corrupted(x: BinaryTree): BinaryTree

    Corrupt input

    Corrupt input

    x

    input to be corrupted

    returns

    corrupted input

    Definition Classes
    TreeType → ManipulationType

  8. def different(x: Null, y: Null): Boolean

    Check whether given two are same or not.

    Check whether given two are same or not.

    x

    Out-type object

    y

    Out-type object

    returns

    True if they are different.

    Definition Classes
    ManipulationType

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

    Definition Classes
    AnyRef

  10. def equals(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any

  11. val error: Objective

    An objective function (Default: kr.ac.kaist.ir.deep.fn.SquaredErr)

    An objective function (Default: kr.ac.kaist.ir.deep.fn.SquaredErr)

    Definition Classes
    RAEType → ManipulationType

  12. def finalize(): Unit

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

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

    Definition Classes
    AnyRef → Any

  14. def hashCode(): Int

    Definition Classes
    AnyRef → Any

  15. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any

  16. def lossOf(net: Network)(pair: (BinaryTree, Null)): Scalar

    Apply given input and compute the error

    Apply given input and compute the error

    net

    A network that gets input

    pair

    (Input, Real output) for error computation.

    returns

    error of this network

    Definition Classes
    RAEType → ManipulationType

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

    Definition Classes
    AnyRef

  18. final def notify(): Unit

    Definition Classes
    AnyRef

  19. final def notifyAll(): Unit

    Definition Classes
    AnyRef

  20. def onewayTrip(net: Network, x: BinaryTree): ScalarMatrix

    Apply given single input as one-way forward trip.

    Apply given single input as one-way forward trip.

    net

    A network that gets input

    x

    input to be computed

    returns

    output of the network.

    Definition Classes
    TreeType → ManipulationType

  21. def roundTrip(net: Network, in: BinaryTree, real: Null, isPositive: Boolean = true): Unit

    Apply & Back-prop given single input

    Apply & Back-prop given single input

    net

    A network that gets input

    in

    Input for error computation.

    real

    Real Output for error computation.

    isPositive

    *(Unused)* Boolean that indicates whether this example is positive or not. We don't need this because RAE does not get negative input.

    Definition Classes
    RAEType → ManipulationType

  22. def stringOf(net: Network, pair: (BinaryTree, Null)): String

    Make validation output

    Make validation output

    net

    A network that gets input

    returns

    input as string

    Definition Classes
    RAEType → ManipulationType

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

    Definition Classes
    AnyRef

  24. def toString(): String

    Definition Classes
    AnyRef → Any

  25. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from TreeType

Inherited from ManipulationType[BinaryTree, Null]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped