Example:
Clustering Problem using a Self-Organizing Map (demo.m)
close all, clear all, clc, format compact load simplecluster_dataset;
% a 2x1000 matrix of 1000 two-element vectors. x = simpleclusterInputs; % plot clusters figure, plot(x(1,:),x(2,:),'g.'); hold on
grid on
% Create a Self-Organizing Map dim1 = 10; dim2 = 10;
net = selforgmap([dim1 dim2]); % Train the Network
[net,tr] = train(net,x);
% View the Network view(net) % Plots figure, plotsomtop(net) figure, plotsomnc(net) figure, plotsomnd(net) figure, plotsomplanes(net) figure, plotsomhits(net,x)
figure, plotsompos(net,x)
Exercise:
Define 4 clusters of input data with the following piece of code, and plot input data using your own codes;
% number of samples of each cluster
K = 200; % offset of classes q = 1.1;
% define 4 clusters of input data
P = [rand(1,K)-q rand(1,K)+q rand(1,K)+q rand(1,K)-q; rand(1,K)+q rand(1,K)+q rand(1,K)-q rand(1,K)-q];
%% Your own codes
Create and train 2D-SOM with the following parameters using your own codes, and plot the 2D-SOM results with the following functions (you can also change the parameters accordingly).
% SOM parameters
dimensions = [10 10];
%% Your own codes
% plot input data and SOM weight positions figure, plotsompos(net, P); grid on % plot SOM neighbor distances figure, plotsomnd(net)
% plot for each SOM neuron the number of input vectors that it classifies figure, plotsomhits(net,P)
