Class

com.lewuathe.dllib.layer

Layer

Related Doc: package layer

Permalink

abstract class Layer extends Serializable

Layer is an abstraction of neural network layer. This class only retains the size of input and output not coefficient and intercept. Actual parameters are kept in Model class. The parameters can be accessed with id.

Linear Supertypes
Serializable, Serializable, AnyRef, Any
Known Subclasses
AffineLayer, DenoisingAutoEncodeLayer, PretrainLayer, ReLULayer, ShapeValidator, SigmoidLayer, SoftmaxLayer, Visualizable
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Layer
  2. Serializable
  3. Serializable
  4. AnyRef
  5. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Layer()

    Permalink

Abstract Value Members

  1. abstract def backward(delta: Vector[Double], acts: ActivationStack, model: Model): (Vector[Double], Weight, Bias)

    Permalink

    Calculate the delta of this iteration.

    Calculate the delta of this iteration. The input of the layer in forward phase can be restored from ActivationStack. It returns the delta of input layer of this layer and the delta of coefficient and intercept parameter.

    returns

    The delta tuple of the layer while back propagation. First is passed previous layer, the second and third is the delta of Weight and Bias parameter of the layer.

  2. abstract def forward(acts: ActivationStack, model: Model): Vector[Double]

    Permalink

    Calculate the output corresponding given input.

    Calculate the output corresponding given input. Input is given as a top of ActivationStack.

    returns

    The output tuple of the layer.

  3. abstract val id: String

    Permalink

  4. abstract val inputSize: Int

    Permalink

  5. abstract val outputSize: Int

    Permalink

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. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  5. def clone(): AnyRef

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

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

    Permalink
    Definition Classes
    AnyRef

  7. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  8. def finalize(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef → Any

  10. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  11. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

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

    Permalink
    Definition Classes
    AnyRef

  13. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  14. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

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

    Permalink
    Definition Classes
    AnyRef

  16. def toString(): String

    Permalink
    Definition Classes
    Layer → AnyRef → Any

  17. final def wait(): Unit

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

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

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

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

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

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped