Inhibition and the output map of MVQ neural networks

We complete the design process of the multiple class vector quantization (MVQ) neural network. The focus of this study is the design of the output layer. The output layer is a group of significant neurons sets. Each set has its own mapping function to the output. The inhibition function enables a single mapping to the output. We also present the canonical architecture of the MVQ network that allows a mix of neurons and the use of higher order moments.