TY - JOUR
T1 - Learning smooth dendrite morphological neurons for pattern classification using linkage trees and evolutionary-based hyperparameter tuning
AU - Tovias-Alanis, Samuel Omar
AU - Sossa, Humberto
AU - Gómez-Flores, Wilfrido
N1 - Publisher Copyright:
© 2023
PY - 2023/8
Y1 - 2023/8
N2 - The current learning approach for smooth dendrite morphological neurons (DMNs) determines dendrite parameters using k-means clustering, which is non-reproducible due to its stochastic nature, risking falling into local minima. To overcome this issue, we introduce a DMN learning approach based on a deterministic hierarchical clustering method, which builds a linkage tree for each class of patterns. In addition, a micro genetic algorithm automatically tunes the cut-off points in the linkage trees hierarchy to create suitable clusters of dendrites. The classification experiments consider 40 real-world datasets. The proposed approach outperforms three DMN models in classification performance and is quite competitive with a hybrid morphological-linear perceptron, multilayer perceptron, random forest, and support vector machine. Therefore, the proposed method is a suitable alternative for pattern classification applications.
AB - The current learning approach for smooth dendrite morphological neurons (DMNs) determines dendrite parameters using k-means clustering, which is non-reproducible due to its stochastic nature, risking falling into local minima. To overcome this issue, we introduce a DMN learning approach based on a deterministic hierarchical clustering method, which builds a linkage tree for each class of patterns. In addition, a micro genetic algorithm automatically tunes the cut-off points in the linkage trees hierarchy to create suitable clusters of dendrites. The classification experiments consider 40 real-world datasets. The proposed approach outperforms three DMN models in classification performance and is quite competitive with a hybrid morphological-linear perceptron, multilayer perceptron, random forest, and support vector machine. Therefore, the proposed method is a suitable alternative for pattern classification applications.
KW - Dendrite morphological neurons
KW - Genetic algorithm
KW - Linkage trees
KW - Pattern classification
KW - Spherical dendrites
UR - http://www.scopus.com/inward/record.url?scp=85160802738&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2023.05.024
DO - 10.1016/j.patrec.2023.05.024
M3 - Artículo
AN - SCOPUS:85160802738
SN - 0167-8655
VL - 172
SP - 274
EP - 281
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
ER -