To reject or not to reject: That is the question - An answer in case of neural classifiers
To reject or not to reject: That is the question - An answer in case of neural classifiers
复制标题
DOI：
10.1109/5326.827457
复制
发表时间：
2000-02-01
期刊：
影响因子：
--
通讯作者：
Vento, M
中科院分区：
文献类型：
--
作者：
De Stefano, C;Sansone, C;Vento, M
本文提出了一种适用于给定ii-拒绝分类器的拒绝选项定义方法。拒绝选项是基于对分类可靠性的估计；由可靠性评估器Psi测量。简单地说，一旦拒绝阈值sigma被固定。如果Psi的相应值低于sigma，则样品被拒绝。显然，由于sigma代表了最小可容忍的分类可靠性水平，当它的值变化时，拒绝选项变得或多或少严重。为了使拒绝选项的行为适应所考虑的应用程序领域的需求，引入了一个函数P来表征拒绝选项对该领域的充分性。结果表明，P可以表示为sigma的函数，因此，sigma的最优值定义为使函数P最大化的值。确定最优阈值的方法与特定的0拒绝分类器无关。虽然可靠性评估器的定义与分类器的体系结构有关，但本文阐述了在分类范式中定义适当的可靠性评估器的一般标准，这些标准是基于可能被分类为低可靠性的样本在特征空间中的定位。三种流行的神经网络体系结构的可靠性评估器的定义。介绍了反向传播、学习向量量化和概率神经网络。最后，结合一个复杂的分类问题对该方法进行了验证，该分类问题的数据是根据分布模型的分布生成的。
In this paper a method defining a reject option applicable to a given ii-reject classifier is proposed. The reject option is based on an estimate of the classification reliability; measured by a reliability evaluator Psi. Trivially once a reject threshold sigma has been fixed. a sample is rejected if the corresponding value of Psi is below sigma. Obviously, as sigma represents the least tolerable classification reliability level, when its value varies the reject option becomes more or less severe. In order to adapt the behavior of the reject option to the requirements of the considered application domain, a function P characterizing the reject option's adequacy to the domain has been introduced. It is shown that P can be expressed as a function of sigma and, consequently, the optimal value for sigma is defined as the one which maximizes the function P.The method for determining the optimal threshold value is independent of the specific 0-reject classifier, while the definition of the reliability evaluators is related to the classifier's architecture,General criteria for defining appropriate reliability evaluators within a classification paradigm are illustrated in the paper and are based on the localization, in the feature space, of the samples that could be classified with a low reliability. The definition of the reliability evaluators for three popular architectures of neural networks. back-propagation, learning vector quantization and probabilistic neural network, is presented.Finally, the method has been tested with reference to a complex classification problem with data generated according to a distribution of distribution model.