smile.vq

Interface Neighborhood

All Superinterfaces:

java.io.Serializable

public interface Neighborhood
extends java.io.Serializable

The neighborhood function for 2-dimensional lattice topology (e.g. SOM). It determines the rate of change around the winner neuron.

Method Summary

Modifier and Type	Method and Description
static Neighborhood	bubble(int radius) Returns the bubble neighborhood function.
static Neighborhood	Gaussian(double sigma, double T) Returns Gaussian neighborhood function.
double	of(int i, int j, int t) Returns the changing rate of neighborhood at a given iteration.

Method Detail

of

double of(int i,
          int j,
          int t)

Returns the changing rate of neighborhood at a given iteration.

Parameters:

i - the row distance of topology from the the winner neuron.

j - the column distance of topology from the the winner neuron.

t - the order number of current iteration.

bubble

static Neighborhood bubble(int radius)

Returns the bubble neighborhood function. The bubble neighborhood function is a constant function in the defined neighborhood of the winner neuron, that is, every neuron in the neighborhood is updated the same proportion of the difference between the neuron and the presented sample vector. The bubble neighborhood function is a good compromise between the computational cost and the approximation of the Gaussian.

Parameters:

radius - the radius of neighborhood.

Gaussian

static Neighborhood Gaussian(double sigma,
                             double T)

Returns Gaussian neighborhood function.

Parameters:

sigma - the initial radius of neighborhood.

T - the number of iterations.