DVCC-based feed-forward neural network for sorting of numbers

Ordering of a set of numbers based on their relative magnitudes is a much used operation in computation tasks. A DVCC-based neural circuit for ranking a given set of numbers is presented. The proposed network is CMOS compatible by virtue of the use of Differential Voltage Current Conveyors and CMOS opamps, does not require any feedback connection, requires fewer neurons, and fewer interconnections between neurons as compared to existing schemes. Further, the numbers to be sorted are directly applied as inputs to the circuit unlike some existing schemes requiring the setting of initial conditions to load the numbers to be sorted. Results of PSPICE simulation confirm the theory proposed.