论文标题
MNIST-NET10：基于确定性程度达到0.1错误率的异质深网络融合。合奏概述和建议
MNIST-NET10: A heterogeneous deep networks fusion based on the degree of certainty to reach 0.1 error rate. Ensembles overview and proposal
论文作者
论文摘要
集合方法已被广泛用于改善最佳单个分类模型的结果。大量作品主要通过应用一种特定的合奏方法来取得更好的性能。但是，很少有作品使用具有新的聚合策略的HET脱离合奏来探索复杂的融合方案。本文是三倍：1）它概述了最受欢迎的合奏方法，2）使用MNIST作为指导线来分析几种融合方案，而3）引入MNIST-NET10，这是一种基于一定程度的确定性聚集方法，这是一种复杂的异质融合体系结构；它从数据，模型和融合策略的角度结合了两个异质方案。 MNIST-NET10仅在MNISTWITH中获得新的记录，仅10个错误分类的图像。我们的分析表明，基于确定性程度的这种复杂的异质融合构型可以被视为一种受益于个人的好处。
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) 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 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.
