Learning Vector Quantization Networks :: Self-Organizing and Learn. Vector Quant. Nets (Neural Network Toolbox)

Neural Network Toolbox

Learning Vector Quantization Networks

LVQ networks classify input vectors into target classes by using a competitive layer to find subclasses of input vectors, and then combining them into the target classes.

Unlike perceptrons, LVQ networks can classify any set of input vectors, not just linearly separable sets of input vectors. The only requirement is that the competitive layer must have enough neurons, and each class must be assigned enough competitive neurons.

To ensure that each class is assigned an appropriate amount of competitive neurons, it is important that the target vectors used to initialize the LVQ network have the same distributions of targets as the training data the network is trained on. If this is done, target classes with more vectors will be the union of more subclasses.

Summary Figures