optimization method of radial basis neural network , newrb function

I am working on radial basis neural network with newrb function. I wondered what kind of optimization method is used to find the input weights. It's similar to the least square error but not exactly the same. Thanks

Answer 1

[Greg Heath]

The code is given in

type newrb

Each epoch the worst performing vector is added to the hidden layer as a Gaussian transfer function center to improve performance.

Hope this helps.

Thank you for formally accepting my answer.

Greg