Genetic algorithms outperform gradient descent when training DEBI-NN on synthetic and small medical datasets (n=85 to 2126), achieving accuracies of 100% vs 83%, 83% vs 78%, 80% vs 67%, and 81% vs 66%.
Papp, Mastering Distance-Encoding Biomorphic Neural Networks – The DEBI-NN Handbook, Zenodo, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Genetic algorithm vs. gradient descent for training a neural network architecture dedicated to low data regimes in small medical datasets
Genetic algorithms outperform gradient descent when training DEBI-NN on synthetic and small medical datasets (n=85 to 2126), achieving accuracies of 100% vs 83%, 83% vs 78%, 80% vs 67%, and 81% vs 66%.