Saved in:
Bibliographic Details
Main Authors: Cunha, Iara, Valle, Marcos Eduardo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.05697
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912574515183616
author Cunha, Iara
Valle, Marcos Eduardo
author_facet Cunha, Iara
Valle, Marcos Eduardo
contents A morphological perceptron is a multilayer feedforward neural network in which neurons perform elementary operations from mathematical morphology. For multiclass classification tasks, a morphological perceptron with a competitive layer (MPCL) is obtained by integrating a winner-take-all output layer into the standard morphological architecture. The non-differentiability of morphological operators renders gradient-based optimization methods unsuitable for training such networks. Consequently, alternative strategies that do not depend on gradient information are commonly adopted. This paper proposes the use of the convex-concave procedure (CCP) for training MPCL networks. The training problem is formulated as a difference of convex (DC) functions and solved iteratively using CCP, resulting in a sequence of linear programming subproblems. Computational experiments demonstrate the effectiveness of the proposed training method in addressing classification tasks with MPCL networks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05697
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Morphological Perceptron with Competitive Layer: Training Using Convex-Concave Procedure
Cunha, Iara
Valle, Marcos Eduardo
Machine Learning
Optimization and Control
A morphological perceptron is a multilayer feedforward neural network in which neurons perform elementary operations from mathematical morphology. For multiclass classification tasks, a morphological perceptron with a competitive layer (MPCL) is obtained by integrating a winner-take-all output layer into the standard morphological architecture. The non-differentiability of morphological operators renders gradient-based optimization methods unsuitable for training such networks. Consequently, alternative strategies that do not depend on gradient information are commonly adopted. This paper proposes the use of the convex-concave procedure (CCP) for training MPCL networks. The training problem is formulated as a difference of convex (DC) functions and solved iteratively using CCP, resulting in a sequence of linear programming subproblems. Computational experiments demonstrate the effectiveness of the proposed training method in addressing classification tasks with MPCL networks.
title Morphological Perceptron with Competitive Layer: Training Using Convex-Concave Procedure
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2509.05697