Opposite neighborhood: a new method to select reference points of minimal learning machines
This paper introduces a new approach to select reference points in minimal learning machines (MLMs) for classification tasks. The MLM training procedure comprises the selection of a subset of the data, named reference points (RPs), that is used to build a linear regression model between distances taken in the input and output spaces. In this matter, we propose a strategy, named opposite neighborhood (ON), to tackle the problem of selecting RPs by locating RPs out of class-overlapping regions. Experiments were carried out using UCI data sets. As a result, the proposal is able to both produce sparser models and achieve competitive performance when compared to the regular MLM.
PDF Abstract