SORT: a fast and compact neural classifier based on a sorting preprocessor

This paper proposes a compact neural classifier, based on the theory of simplicial decomposition and approximation, with a very convenient hardware or software implementation. It can learn arbitrary n-inputs patterns with O(n) time complexity. There are no multipliers required, and the learned knowledge is stored in a general purpose RAM with a size ranging from O(n) to O(n²). The proposed architecture is composed only of three building blocks, a sorter, a RAM memory and an accumulator, all of them readily available in either digital hardware or software technology. Simulation results indicate good accuracy for a wide variety of benchmark problems.