.png){kind=icon}
返回
Activation-Based Cause Analysis Method for Neural Networks
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2021.3103322.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As neural networks are ubiquitous in the real-world environment, we encounter a variety of situations in which neural network-based systems fail. To address these failures, we need to identify their root causes. However, due to the black-box nature of neural networks, it is considered a difficult task to explain/understand internal functions, and cause analysis is usually conducted based on personal experience. To alleviate these problems, we propose a method to compute an element-wise contribution of inputs on current decisions. To this end, we focus on the physical meaning of neuron activations, and formulate an optimization problem that finds partial activations that support current decisions. Then, by accumulating these partial activations in the backward direction, we evaluate the contributions of each element in an input vector to the current decision. Experimental results have shown that the proposed method outperforms conventional methods in terms of cause localization for a range of failure scenarios.
Keyword:
Perturbation methods
Neurons
Biological neural networks
Visualization
Licenses
Computational modeling
Training
Multilayer perceptron
interpretable machine learning
explaining classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Cell-free Protein Synthesis in an Autoinduction System for NMR Studies of Protein–Protein Interactions用于NMR研究蛋白质-蛋白质相互作用的自动诱导系统中的无细胞蛋白质合成
PREAI
分享收藏Fuzziness-based online sequential extreme learning machine for classification problems.png)
SOFT COMPUTING
SOFT COMPUTINGIF2.5
PREAI
分享收藏Subsequent Pain or Injury After Foot and Ankle Surgery in Patients Receiving Workers’ CompensationOAAI
OAAI分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Sensitivity of excess mortality due to the COVID-19 pandemic to the choice of the mortality index, method, reference period, and the time unit of the death series新型冠状病毒肺炎大流行导致的超额死亡率对死亡率指数、方法、参考期和死亡序列时间单位选择的敏感性
OAAI
IF0
OAAI分享收藏
查看更多内容