Invariances have to be dynamically estimated from data.

The competition in upper subnet of hamming network continues till output of only one unit remains positive.

The objective of associative memories is to store association between patterns for later recall of one of patterns given the other, so noisy versions of the same image can be recalled.

Hamming network performs template matching between stored templates and inputs.

Simply, greater the degradation less is the activation value of winning units.

Optimization be applied in images by use of simulated annealing to formulate the problem as energy minimization problem.

Because of their parallel structure, they have high computational rates than conventional computers, so all are true.

It can only perform pattern recognition, rest is not true for a single layer neural.

Its is the most direct and multilayer feedforward networks became popular because of this.

Matching score is simply a indicative of similarity of input pattern with patterns stored.