From Classical Connectionist Models to Probabilistic/Generalised Regression Neural Networks (PNNs/GRNNs)

Abstract

This chapter begins by briefly summarising some of the well-known classical connectionist/artificial neural network models such as multi-layered perceptron neural networks (MLP-NNs), radial basis function neural networks (RBF-NNs), self-organising feature maps (SOFMs), associative memory, and Hopfield-type recurrent neural networks (HRNNs). These models are shown to normally require iterative and/or complex parameter approximation procedures, and it is highlighted why these approaches have in general lost interest in modelling the psychological functions and developing artificial intelligence (in a more realistic sense).