Probabilistic neural networks

Probabilistic neural networks


Input layer

The input is the feature vector.

Pattern layer

The first layer has a node for each observation in the training set.

In each node, the value is the distance from the input to the comparator.

This can be calculated using Gaussian distribution, or another method.

Summation layer

One neuron for each category.

We map from the pattern layer to the summation layer according to the actual label of each training item.

Ie, if a sample is red, it will be fed only to the red neuron.

The values are summed.

Largest value is selected.