Learning smooth dendrite morphological neurons for pattern classification using linkage trees and evolutionary-based hyperparameter tuning

•Dendrite morphological neuron learning is based on deterministic linkage trees.•Linkage trees overcome k-means’ non-reproducibility in learning dendrites’ locations.•A micro genetic algorithm speeds up the automatic hyperparameter tuning of models.•A balanced fitness function favors solutions with a low error rate and few dendrites.•The proposed approach beats its counterparts related to accuracy and model complexity.