Cognitive networks for automated target recognition and autonomous system applications

It is shown that in order to be truly cognitive a network must be nonlinear and dynamical and able to manifest bifurcation. This means it should be able to carry out phase-space computations with more than one type of attractor and to switch between these depending on whether the sensory input is familiar or novel. Cognition therefore implies bifurcation and computing with diverse attractors. Reasons for adopting this view, which stemmed from known biophysical observations and from neuromorphic target identification work, are discussed. An example of a cognitive network that computes with both stationary (limit point) and dynamic (periodic) attractors is given to illustrate the thesis presented. The elements of a neuromorphic radar target identification system which employs these concepts and is capable of distortion-invariant recognition of three targets with perfect score are presented. The role of periodic attractors in feature binding and cognition and the significance of cognition in autonomous systems are elucidated