Abstract
Presented is a new paradigm for artificial neural system (ANS) design. The theoretical basis employs a novel concept whereby information is represented by phase angle orientations on a Riemann plane. Central to the theory of operation is the principle of information storage and expression in the form of stimulus-response patterns. The governing equations form a nonconnectionist approach in which a very large number of analog stimulus-response patterns or associations may be superimposed or enfolded onto a single neural element. The system indicates a mechanism by which the above associations may be both encoded and expressed on one noniterative transformation. A broad analogy may be made to digital holography1 in the form of the constitutive equations and some general operating characteristics. Simulation results for the system indicate information storage capacities and effective rates of processing orders of magnitude beyond current ANS theory. Many observable characteristics are displayed by the system which suggest that the analytical method may provide insight into the information processing mechanism occurring within neurobiological systems.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
