Design of effective neural network ensembles for image classification purposes
Design of effective neural network ensembles for image classification purposes
复制标题
DOI：
10.1016/s0262-8856(01)00045-2
复制
发表时间：
2001-08-01
影响因子：
4.7
通讯作者：
Roli, F
中科院分区：
文献类型：
--
作者：
Giacinto, G;Roli, F
在模式识别领域，已经提出了神经网络集成的组合作为开发高性能图像分类系统的方法。然而，以前的工作清楚地表明，只有当形成它们的神经网络产生不同的错误时，这种图像分类系统才是有效的。因此，目前公认的基本需要的方法，旨在设计合奏的“错误无关”的网络。本文提出了一种有效的神经网络集成的自动设计方法。给定一个初始的大的神经网络集，我们的方法的目的是选择最错误的独立网络形成的子集。多传感器遥感图像的分类结果表明，这种方法可以设计有效的神经网络集成。(C)2001 Elsevier Science B.V.保留所有权利。
In the field of pattern recognition, the combination of an ensemble of neural networks has been proposed as an approach to the development of high performance image classification systems. However, previous work clearly showed that such image classification systems are effective only if the neural networks forming them make different errors. Therefore, the fundamental need for methods aimed to design ensembles of 'error-independent' networks is currently acknowledged. In this paper, an approach to the automatic design of effective neural network ensembles is proposed. Given an initial large set of neural networks, our approach is aimed to select the subset formed by the most error-independent nets. Reported results on the classification of multisensor remote-sensing images show that this approach allows one to design effective neural network ensembles. (C) 2001 Elsevier Science B.V. All rights reserved.