MNIST-NET10: A heterogeneous deep networks fusion based on the degree of certainty to reach 0.1 error rate. Ensembles overview and proposal [article]

S. Tabik, R.F. Alvear-Sandoval, M.M. Ruiz, J.L. Sancho-Gómez, A.R. Figueiras-Vidal, F. Herrera
2020 arXiv   pre-print
Ensemble methods have been widely used for improving the results of the best single classificationmodel. A large body of works have achieved better performance mainly by applying one specific ensemble method. However, very few works have explored complex fusion schemes using het-erogeneous ensembles with new aggregation strategies. This paper is three-fold: 1) It provides an overview of the most popular ensemble methods, 2) analyzes several fusion schemes using MNIST as guiding thread and 3)
more » ... roduces MNIST-NET10, a complex heterogeneous fusion architecture based on a degree of certainty aggregation approach; it combines two heterogeneous schemes from the perspective of data, model and fusion strategy. MNIST-NET10 reaches a new record in MNISTwith only 10 misclassified images. Our analysis shows that such complex heterogeneous fusionarchitectures based on the degree of certainty can be considered as a way of taking benefit fromdiversity.
arXiv:2001.11486v2 fatcat:ji7ovh6mwvdjzgb3dwhpuqmike