The Hamming network executes the task of style association, or classification, depending on measuring the

Hamming distance. The network is a pattern connect of n-dimensional binary vectors labeled with m-class labels (m-class patterns).

A new vector x' is associated with class pattern xi with the minimum Hamming distance, a Hamming distance being the quantity of different bits in the two patterns. The Hamming network is comparable to the Hopfield network, but it has two layers of connections. The very first layer contains connections between all the n inputs, and all the m outputs. The 2nd layer is a fully connected recurrent network with m neurons (comparable to the Hopfield network). Almost all nodes use linear threshold activation functions.