Packages

object Initializer

The Initializer object provides functions to initialize the parameters/weights of Neural Networks. Supports Uniform, Normal and Nguyen & Widrow methods.

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Initializer
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Value Members

  1. def weightMat(rows: Int, cols: Int, stream: Int = 0, limit: Double = -1.0): MatriD

    Generate a random weight/parameter matrix with elements values in (0, limit).

    Generate a random weight/parameter matrix with elements values in (0, limit).

    rows

    the number of rows

    cols

    the number of columns

    stream

    the random number stream to use

    limit

    the maximum value for any weight

  2. def weightMat2(rows: Int, cols: Int, stream: Int = 0): MatriD

    Generate a random weight/parameter matrix with elements values from the Standard Normal distribution.

    Generate a random weight/parameter matrix with elements values from the Standard Normal distribution.

    rows

    the number of rows

    cols

    the number of columns

    stream

    the random number stream to use

  3. def weightMat3(rows: Int, cols: Int, stream: Int = 0): MatriD

    Generate a random weight/parameter matrix with elements values from the Nguyen & Widrow method.

    Generate a random weight/parameter matrix with elements values from the Nguyen & Widrow method.

    rows

    the number of rows

    cols

    the number of columns

    stream

    the random number stream to use

    See also

    ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6945481

  4. def weightVec(rows: Int, stream: Int = 0, limit: Double = -1.0): VectoD

    Generate a random weight/parameter matrix with elements values in (0, limit).

    Generate a random weight/parameter matrix with elements values in (0, limit).

    rows

    the number of rows

    stream

    the random number stream to use

    limit

    the maximum value for any weight

  5. def weightVec2(rows: Int, stream: Int = 0): VectoD

    Generate a random weight/parameter matrix with elements values from the Standard Normal distribution.

    Generate a random weight/parameter matrix with elements values from the Standard Normal distribution.

    rows

    the number of rows

    stream

    the random number stream to use

  6. def weightVec3(rows: Int, stream: Int = 0): VectoD

    Generate a random weight/parameter matrix with elements values from the Nguyen & Widrow Method.

    Generate a random weight/parameter matrix with elements values from the Nguyen & Widrow Method.

    rows

    the number of rows

    stream

    the random number stream to use

    See also

    ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6945481