We propose a new classifier based on Dempster-Shafer (DS) theory and a convolutional neural network (CNN) architecture for set-valued classification. In this classifier, called the evidential deep-learning classifier, convolutional and pooling layers first extract high-dimensional features from input data. The features are then converted into mass functions and aggregated by Dempster's rule in a DS layer. Finally, an expected utility layer performs set-valued classification based on mass functions. We propose an end-to-end learning strategy for jointly updating the network parameters. Additionally, an approach for selecting partial multi-class acts is proposed. Experiments on image recognition, signal processing, and semantic-relationship classification tasks demonstrate that the proposed combination of deep CNN, DS layer, and expected utility layer makes it possible to improve classification accuracy and to make cautious decisions by assigning confusing patterns to multi-class sets.
翻译:我们根据Dempster-Shafer (DS) 理论提出一个新的分类器,并提议一个用于定值分类的进化神经网络(CNN)结构。在这个分类器中,我们称为证据深学习分类器、进化和集合层,首先从输入数据中提取高维特征。这些特征随后转换成质量功能,然后由Dempster的规则在DS层中加以汇总。最后,预期的公用事业层根据质量功能进行定值分类。我们提议了一个端到端学习战略,以共同更新网络参数。此外,还提议了一个选择部分多级行为的方法。关于图像识别、信号处理和语义-关系分类的实验表明,拟议的深CNN、DS层和预期的效用层组合使得有可能提高分类的准确性,并通过将混淆模式分配给多级数据集来作出谨慎的决定。