A modified probabilistic neural network signal processor for nonlinear signals

This paper introduces a practical and very effective network for nonlinear signal processing called the modified probabilistic neural network. It is a regression technique which uses a single radial basis function kernel whose bandwidth is related to the noise statistics. It has special advantages in application to time and spatial series signal processing problems because it is constructed directly and simply for the training signal waveform features. A sonar signal processing problem is used to illustrate its operation and to compare it with some other filters and neural networks