Class-modular multi-layer perceptions, task decomposition and virtually balanced training subsets

Abstract

This paper focuses on how to use class-modular single-hidden-layer perceptrons (MLPs) with sigmoid activation functions (SAFs) to solve the multi-class learning problems, and pays special attention to the unbalanced data sets. Our solutions are as follows. (A) An n-class learning problem first decomposes into n two-class problems (B) A single-output MLP is responsible for solving a two-class problem, separating its represented class with all the other classes, and trained only by the samples from the represented class and some neighboring ones. (C) The samples from the minority classes or in the thin regions are virtually reinforced (D)The generalization region of an MLP is localized. The proposed method is verified effective by the experimental result of letter recognition.