Morphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm

P Sussner, EL Esmi - Information Sciences, 2011 - Elsevier
A morphological neural network is generally defined as a type of artificial neural network that
performs an elementary operation of mathematical morphology at every node, possibly …

An overview of some classical growing neural networks and new developments

X Qiang, G Cheng, Z Wang - 2010 2nd International …, 2010 - ieeexplore.ieee.org
The map** capability of artificial neural networks (ANN) is dependent on their structure, ie,
the number of layers and the number of hidden units. There is no formal way of computing …

Differential evolution training algorithm for dendrite morphological neural networks

F Arce, E Zamora, H Sossa, R Barrón - Applied Soft Computing, 2018 - Elsevier
Dendrite morphological neural networks are emerging as an attractive alternative for pattern
classification, providing competitive results with other classification methods. A key problem …

Extreme learning machine for a new hybrid morphological/linear perceptron

P Sussner, I Campiotti - Neural Networks, 2020 - Elsevier
Morphological neural networks (MNNs) can be characterized as a class of artificial neural
networks that perform an operation of mathematical morphology at every node, possibly …

Discrete morphological neural networks

D Marcondes, J Barrera - SIAM Journal on Imaging Sciences, 2024 - SIAM
A classical approach to designing binary image operators is mathematical morphology
(MM). We propose the Discrete Morphological Neural Networks (DMNN) for binary image …

Piecewise-linear approximation of non-linear models based on probabilistically/possibilistically interpreted intervals' numbers (INs)

SE Papadakis, VG Kaburlasos - Information Sciences, 2010 - Elsevier
Linear models are preferable due to simplicity. Nevertheless, non-linear models often
emerge in practice. A popular approach for modeling nonlinearities is by piecewise-linear …

Dendrite ellipsoidal neurons based on k-means optimization

F Arce, E Zamora, C Fócil-Arias, H Sossa - Evolving Systems, 2019 - Springer
Dendrite morphological neurons are a type of artificial neural network that can be used to
solve classification problems. The major difference with respect to classical perceptrons is …

Bipolar morphological neural networks: convolution without multiplication

E Limonova, D Matveev, D Nikolaev… - … on Machine Vision …, 2020 - spiedigitallibrary.org
In the paper we introduce a novel bipolar morphological neuron and bipolar morphological
layer models. The models use only such operations as addition, subtraction and maximum …

Swarm-based translation-invariant morphological prediction method for financial time series forecasting

RA Araújo - Information Sciences, 2010 - Elsevier
In this paper, we present a method to overcome the random walk (RW) dilemma for financial
time series forecasting, called swarm-based translation-invariant morphological prediction …

On machine-learning morphological image operators

NST Hirata, GA Papakostas - Mathematics, 2021 - mdpi.com
Morphological operators are nonlinear transformations commonly used in image
processing. Their theoretical foundation is based on lattice theory, and it is a well-known …