Linear Dilation-Erosion Perceptron for Binary Classification
This is an incremental improvement for binary classification tasks in machine learning.
The authors tackled binary classification by introducing a linear dilation-erosion perceptron (l-DEP) that applies a linear transformation before morphological operators, and they trained it using a regularized hinge-loss function with concave-convex restrictions, resulting in a simple illustrative example.
In this work, we briefly revise the reduced dilation-erosion perceptron (r-DEP) models for binary classification tasks. Then, we present the so-called linear dilation-erosion perceptron (l-DEP), in which a linear transformation is applied before the application of the morphological operators. Furthermore, we propose to train the l-DEP classifier by minimizing a regularized hinge-loss function subject to concave-convex restrictions. A simple example is given for illustrative purposes.