Construction of Minimal Multi-Layered Perceptrons: A Case Study for Sorting

摘要

The construction of minimal multilayered perceptrons for solving combinatorialoptimization problems is considered. The construction method is presented as a case study for the sorting problem. The presentation starts with an O((n factorial) squared) three layered perceptron based on complete enumeration, that solves the sorting problem of n numbers. This network is then gradually reduced to an O(n squared) three layered perceptron which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm.