jsat.datatransform

Enum FastICA.DefaultNegEntropyFunc

java.lang.Object

java.lang.Enum<FastICA.DefaultNegEntropyFunc>

jsat.datatransform.FastICA.DefaultNegEntropyFunc

All Implemented Interfaces:

Serializable, Comparable<FastICA.DefaultNegEntropyFunc>, FastICA.NegEntropyFunc

Enclosing class:

FastICA

public static enum FastICA.DefaultNegEntropyFunc
extends Enum<FastICA.DefaultNegEntropyFunc>
implements FastICA.NegEntropyFunc

A set of default negative entropy functions as specified in the original FastICA paper

Enum Constant Summary

Enum Constants

Enum Constant and Description
EXP This is function G2 in the paper, and according to the paper may be better than LOG_COSH "when the independent components are highly super-Gaussian, or when robustness is very important"
KURTOSIS This is the kurtosis-based approximation function G3(x) = 1/4*x4.
LOG_COSH This is function G1 in the paper.

Method Summary

Modifier and Type	Method and Description
abstract double	deriv1(double x)
abstract double	deriv2(double x, double d1)
static FastICA.DefaultNegEntropyFunc	valueOf(String name) Returns the enum constant of this type with the specified name.
static FastICA.DefaultNegEntropyFunc[]	values() Returns an array containing the constants of this enum type, in the order they are declared.

Methods inherited from class java.lang.Enum

clone, compareTo, equals, finalize, getDeclaringClass, hashCode, name, ordinal, toString, valueOf

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Enum Constant Detail

LOG_COSH

public static final FastICA.DefaultNegEntropyFunc LOG_COSH

This is function G₁ in the paper. This Negative Entropy function is described as a "good general-purpose contrast function" in the original paper, and the default method used.

EXP

public static final FastICA.DefaultNegEntropyFunc EXP

This is function G₂ in the paper, and according to the paper may be better than LOG_COSH "when the independent components are highly super-Gaussian, or when robustness is very important"

KURTOSIS

public static final FastICA.DefaultNegEntropyFunc KURTOSIS

This is the kurtosis-based approximation function G₃(x) = 1/4*x⁴. According to the original paper its use is "is justified on statistical grounds only for estimating sub-Gaussian independent components when there are no outliers."

Method Detail

values

public static FastICA.DefaultNegEntropyFunc[] values()

Returns an array containing the constants of this enum type, in the order they are declared. This method may be used to iterate over the constants as follows:

for (FastICA.DefaultNegEntropyFunc c : FastICA.DefaultNegEntropyFunc.values())
    System.out.println(c);

Returns:

an array containing the constants of this enum type, in the order they are declared

valueOf

public static FastICA.DefaultNegEntropyFunc valueOf(String name)

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)

Parameters:

name - the name of the enum constant to be returned.

Returns:

the enum constant with the specified name

Throws:

IllegalArgumentException - if this enum type has no constant with the specified name

NullPointerException - if the argument is null

deriv1

public abstract double deriv1(double x)

Specified by:

deriv1 in interface FastICA.NegEntropyFunc

Parameters:

x - the input to the function

Returns:

the first derivative of this function

deriv2

public abstract double deriv2(double x,
                              double d1)

Specified by:

deriv2 in interface FastICA.NegEntropyFunc

Parameters:

x - the input to the function

d1 - the first derivative of this function (from FastICA.NegEntropyFunc.deriv1(double))

Returns:

the second derivative of this function