… This article starts with the concept of neuron relevance and proposes a new neural network
explanation method LID-Taylor based on Layer-wise Increment Decomposition. Aiming at …

… reasons for a specific decision. On the other hand, the application of the CNN models in
some high-risk areas also requires a full understanding of the reason for their decisions, so as to …

[目的] 探究基于内容的深度谣言检测模型能否真正识别谣言的关键语义.[方法] 基于谣言检测任务
的中英文基准数据集, 本文分别利用基于局部代理模型的可解释工具LIME 和基于合作博弈论的…

… As the first step, this research designs a deep learning network to retrieve spatial and
spectral features from multi-spectral images and perform the land cover classification. The …

… As a result, this study proposes a simulation-assisted SAR target classification method
based on unsupervised domain adaptation. The proposed method integrates Multi-Kernel …

… 为提高显著性图的清晰度,有学者采用 的形式来计算每个像素的贡献值(arXiv: 1605.01713,
2016),而文献[18]则提出了深度泰勒分解(deep Taylor decomposition)来对f(x)进行关于某个点x 0 的…

… Since the analytic solution of (3.12) is hard to be obtained, we can compute the first-order
Taylor expansion of the second term at βk as an approximation. Suppose gk is the gradient of …

… 为了获得良 好的解释结果, 泰勒分解TD (Taylor decomposition)[41]建议我们选择根点作为参考
… 的启发提出了深度泰勒分解算法DTD (deep Taylor decomposition) 对神经网络进行解释. DTD …

… To expedite the training procedure, we propose to retrain the new SVM classifier by using
only samples classified incorrectly and the critical sets (CSs) from previous samples. After …

… Generally speaking, video complexity analysis is the core component of the bit-allocation
decision of a video encoder. In this thesis, video complexity is further decomposed into visual …