TY - JOUR
T1 - Improving the Classification Performance of Dendrite Morphological Neurons
AU - Gomez-Flores, Wilfrido
AU - Sossa, Humberto
N1 - Publisher Copyright:
IEEE
PY - 2021
Y1 - 2021
N2 - Dendrite morphological neurons (DMNs) are neural models for pattern classification, where dendrites are represented by a geometric shape enclosing patterns of the same class. This study evaluates the impact of three dendrite geometries--namely, box, ellipse, and sphere--on pattern classification. In addition, we propose using smooth maximum and minimum functions to reduce the coarseness of decision boundaries generated by typical DMNs, and a softmax layer is attached at the DMN output to provide posterior probabilities from weighted dendrites responses. To adjust the number of dendrites per class automatically, a tuning algorithm based on an incremental-decremental procedure is introduced. The classification performance assessment is conducted on nine synthetic and 49 real-world datasets. Meanwhile, 12 DMN variants are evaluated in terms of accuracy and model complexity. The DMN reaches its highest potential by combining spherical dendrites with smooth activation functions and a learnable softmax layer. It attained the highest accuracy, uses the simplest geometric shape, is insensitive to variables with zero variance, and its structural complexity diminishes by using the smooth maximum function. Furthermore, this DMN configuration performed competitively or even better than other well-established classifiers in terms of accuracy, such as support vector machine, multilayer perceptron, radial basis function network, k-nearest neighbors, and random forest. Thus, the proposed DMN is an attractive alternative for pattern classification in real-world problems.
AB - Dendrite morphological neurons (DMNs) are neural models for pattern classification, where dendrites are represented by a geometric shape enclosing patterns of the same class. This study evaluates the impact of three dendrite geometries--namely, box, ellipse, and sphere--on pattern classification. In addition, we propose using smooth maximum and minimum functions to reduce the coarseness of decision boundaries generated by typical DMNs, and a softmax layer is attached at the DMN output to provide posterior probabilities from weighted dendrites responses. To adjust the number of dendrites per class automatically, a tuning algorithm based on an incremental-decremental procedure is introduced. The classification performance assessment is conducted on nine synthetic and 49 real-world datasets. Meanwhile, 12 DMN variants are evaluated in terms of accuracy and model complexity. The DMN reaches its highest potential by combining spherical dendrites with smooth activation functions and a learnable softmax layer. It attained the highest accuracy, uses the simplest geometric shape, is insensitive to variables with zero variance, and its structural complexity diminishes by using the smooth maximum function. Furthermore, this DMN configuration performed competitively or even better than other well-established classifiers in terms of accuracy, such as support vector machine, multilayer perceptron, radial basis function network, k-nearest neighbors, and random forest. Thus, the proposed DMN is an attractive alternative for pattern classification in real-world problems.
KW - Brain modeling
KW - Covariance matrices
KW - Dendrite morphological neurons (DMNs)
KW - Dendrites (neurons)
KW - Geometry
KW - Mathematical models
KW - Shape
KW - Training
KW - geometric shape
KW - pattern classification
KW - smooth activation functions
KW - softmax layer.
UR - http://www.scopus.com/inward/record.url?scp=85117139902&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2021.3116519
DO - 10.1109/TNNLS.2021.3116519
M3 - Artículo
C2 - 34623285
AN - SCOPUS:85117139902
SN - 2162-237X
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
ER -