Associative Memory Networks: Adaptive Modelling Theory, Software Implementation and Graphical User Interface

This paper describes in a unified mathematical framework a class of associative memory neural networks (AMN), that have very fast learning rates, local generalisation, parallel implementation, and guaranteed convergence to the mean squared error, making them appropriate for applications such as intelligent control and on-line modelling of nonlinear dynamical processes. The class of AMN considered include the Albus CMAC, B-Splines neural network and classes of fuzzy logic networks. Appropriate instantaneous learning rules are derived and applied to a benchmark nonlinear time series prediction problem. For practical implementation, a network software library and graphical user interface (GUI) is introduced for these networks. The data structure is modular, allowing a natural implementation on a parallel machine. The GUI provides a front end, for high-level procedures, allowing the networks to be designed, trained and analysed within a common environment with a minimum of user effort. The software library is readily integrable into industrial packages such as MATLAB