Correlative type higher-order neural units with applications
Madan M. Gupta · 2008
The computational neural-network structures described in the literature are often based on the concept of linear synaptic operations. In biological process, however, neurons form a set of very complex computing elements and perform much more complex computations than just the linear aggregation. It is well known that the computational efficiency of neural networks depends on its morphology and the learning and adaptation strategies employed. In our engineering design and economic processes neural inputs are not necessarily independent rather they have correlative attributes. In this paper we present a new class of correlative type higher-order neural units (HONUs) with nonlinear combinations of inputs and weights. In particular, in this paper we present a quadratic neural unit (QNU) and a cubic neural unit (CNU). For illustrating the applications of these correlative type higher-order neural units, we have given some examples taken from the field of feedback control systems and logic circuits.