MNIST-NET10: A heterogeneous deep networks fusion based on the degree of certainty to reach 0.1% error rate. ensembles overview and proposal Articles uri icon

publication date

  • January 2020

volume

  • 62

International Standard Serial Number (ISSN)

  • 1566-2535

Electronic International Standard Serial Number (EISSN)

  • 1872-6305

abstract

  • (copyright) 2020 Elsevier B.V.Ensemble methods have been widely used for improving the results of the best single classification model. 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 heterogeneous 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) introduces 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 MNIST with only 10 misclassified images. Our analysis shows that such complex heterogeneous fusion architectures based on the degree of certainty can be considered as a way of taking benefit from diversity.

keywords

  • deep learning; ensemble methods; fusion; mnist