Innovative Production Machines and Systems Conference

Classifier Design

The main advantage of GRNN.

1. The GRNN needs only a single learning pass to achieve optimal performance in classification.

The estimator

1. Use a reduced gaussian kernel

The GRNN operation

1. The input layer simply passes the patterns x to all units in the hidden layers composed by kernels functions  exp(-(D_i²/2 ρ 2)) and computes the squared distances among the new pattern x and xi training samples
2. The hidden-to-output weights are just the targets y_i, thus the output y(x), is simply a weighted average of the target values yi of the training cases x_i close to the given input case x.