Neural Network Toolbox

Graphical Example

Competitive layers can be understood better when their weight vectors and input vectors are shown graphically. The diagram below shows 48 two-element input vectors represented as with `+' markers.

The input vectors above appear to fall into clusters. You can use a competitive network of eight neurons to classify the vectors into such clusters.

Try democ1 to see a dynamic example of competitive learning.

Training

Self-Organizing Maps