Class/Object

com.danylchuk.swiftlearner.nn.backprop

BackpropNet

Related Docs: object BackpropNet | package backprop

Permalink

class BackpropNet extends LazyLogging

A neural network with one hidden layer using backpropagation.

Use BackpropNet.randomNet() to create a new network with random weights.

Ref.: Robert Gordon University, "The Back Propagation Algorithm" https://web.archive.org/web/20150317210621/https://www4.rgu.ac.uk/files/chapter3%20-%20bp.pdf https://en.wikipedia.org/wiki/Backpropagation

Linear Supertypes
LazyLogging, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. BackpropNet
  2. LazyLogging
  3. AnyRef
  4. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new BackpropNet(hiddenLayer: Array[Node], outputLayer: Array[Node])

    Permalink

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 calculateOutput(input: Array[Float]): Array[Float]

    Permalink

    Calculate the result without updating the network

  6. def clone(): AnyRef

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

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

    Permalink
    Definition Classes
    AnyRef

  8. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  9. def finalize(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef → Any

  11. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  12. val hiddenLayer: Array[Node]

    Permalink

  13. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  14. def learn(example: Array[Float], target: Array[Float], rate: Float = 1): BackpropNet

    Permalink

    Learn an example using backpropagation.

    Learn an example using backpropagation.

    rate

    Learning rate. Must be between 0 and 1. Use 1 if in doubt. Smaller values might help converge complex cases sometimes.

  15. def learnSeq(examples: Traversable[(Array[Float], Array[Float])], rate: Float = 1): BackpropNet

    Permalink

    Convenience shortcut for feeding several examples

  16. lazy val logger: Logger

    Permalink
    Attributes
    protected
    Definition Classes
    LazyLogging

  17. val nHidden: Int

    Permalink

  18. val nInput: Int

    Permalink

  19. val nOutput: Int

    Permalink

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

    Permalink
    Definition Classes
    AnyRef

  21. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  22. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  23. val outputLayer: Array[Node]

    Permalink

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

    Permalink
    Definition Classes
    AnyRef

  25. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  26. final def wait(): Unit

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

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

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

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

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

Inherited from LazyLogging

Inherited from AnyRef

Inherited from Any

Ungrouped