Genetic design of discrete dynamical basis networks that approximate data sequences and functions

This paper extends research in the area of biologically inspired, discrete dynamical basis networks (DDBNs). While similar to locally recurrent globally feedforward (LRGF) networks (Tsoi and Back 1994), DDBNs operate at a lower level of abstraction and were inspired by research in the areas of Control systems, Artificial Intelligence, and Neurobiology. As described previously, DDBN's can approximate data sequences and consist of networks of simple, bounded mathematical operators (Jones and Olmsted 2003). This paper examines the characteristics of genetically designed DDBNs and compares them with tree-based genetic programs (TBGPs), biological neural networks, and back-propagation neural networks (NNs). Experimental evidence indicates that DDBNs are capable of computing simple logic functions in addition to approximating data sequences.