The most difficult task in machine learning is to interpret trained shallow neural networks. Deep neural networks (DNNs) provide impressive results on a larger number of tasks, but it is generally still unclear how decisions are made by such a trained deep neural network. Providing feature importance is the most important and popular interpretation technique used in shallow and deep neural networks. In this paper, we develop an algorithm extending the idea of Garson Algorithm to explain Deep Belief Network based Auto-encoder (DBNA). It is used to determine the contribution of each input feature in the DBN. It can be used for any kind of neural network with many hidden layers. The effectiveness of this method is tested on both classification and regression datasets taken from literature. Important features identified by this method are compared against those obtained by Wald chi square (\c{hi}2). For 2 out of 4 classification datasets and 2 out of 5 regression datasets, our proposed methodology resulted in the identification of better-quality features leading to statistically more significant results vis-à-vis Wald \c{hi}2.
Automated and Explainable Denial of Service Analysis for AI-Driven Intrusion Detection Systems
Computer and Information Science Department, Fordham University(福特汉姆大学计算机与信息科学系);RENCI, University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校RENCI);Department of Mathematics and Computer Science, Royal Military College of Canada(加拿大皇家军事学院数学与计算机科学系);Data Science Department, University of North Texas(德克萨斯大学纳夫卡特数据科学系)
Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version
Aalborg University(奥尔堡大学);Huawei Cloud Database Innovation Lab(华为云数据库创新实验室);University of Electronic Science and Technology of China(电子科技大学)
时间序列数据广泛存在,异常点检测是数据采掘的一个基本问题,有着广泛的应用。现有的基于自动编码器的方法在具有挑战性的现实世界数据上提供了最先进的性能,但容易受到离群值的影响,并且表现出较低的可解释性。为了解决这两个限制,我们提出了鲁棒的和可解释的无监督自动编码器框架,使用自动编码器将输入时间序列分解为干净的时间序列和离群值时间序列。由于干净的时间序列可以用易于理解的模式(如趋势和周期性)更好地解释,因此可解释性得到了改善。我们通过事后可解释性分析和实证研究对此进行了深入研究。此外,由于离群值是迭代地从干净的时间序列中分离出来的,我们的方法对离群值提供了更好的鲁棒性,这反过来又提高了准确性。我们在五个真实世界的数据集上评估了我们的方法,并报告了在鲁棒性和可解释性方面对最先进方法的改进。这是“Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection”的扩展版本,将出现在IEEE ICDE 2022中。
Towards Explainable, Safe Autonomous Driving with Language Embeddings for Novelty Identification and Active Learning: Framework and Experimental Analysis with Real-World Data Sets
University of California San Diego(加利福尼亚大学圣迭戈分校);Laboratory for Intelligent and Safe Automobiles(智能与安全汽车实验室)
Deep Distilling: automated code generation using explainable deep learning
Green Center for Systems Biology, University of Texas Southwestern Medical Center(德克萨斯大学西南医学中心格林系统生物学中心);Department of Bioinformatics, University of Texas Southwestern Medical Center(德克萨斯大学西南医学中心生物信息学系);Department of Biophysics, University of Texas Southwestern Medical Center(德克萨斯大学西南医学中心生物物理学系);Department of Biomedical Engineering, Johns Hopkins University(约翰斯·霍普金斯大学生物医学工程系)
Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings
LIX, École Polytechnique(巴黎综合理工学院LIX实验室);Institute Polytechnique de Paris(巴黎理工学院);Université Paris Saclay(巴黎萨克雷大学);Université Paris Cité(巴黎西岱大学);ENS Paris Saclay(巴黎萨克雷高等师范学校);CNRS(法国国家科学研究中心);INSERM(法国国家健康与医学研究院);Centre Borelli(博雷利中心);University of Peloponnese(伯罗奔尼撒大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Explainable Autoencoder-Based Anomaly Detection in IEC 61850 GOOSE Networks
Universidad Rey Juan Carlos(雷奥恩卡洛斯大学);Red Eléctrica (REDEIA Group)(电力公司(REDEIA小组));Centro de Investigación for Data, Complex Networks and Cybersecurity Sciences(数据、复杂网络和网络安全科学研究中心)
Automated detection of motion artifacts in brain MR images using deep learning and explainable artificial intelligence
Columbia University in the City of New York(哥伦比亚大学);GE Healthcare(通用电气医疗);Columbia University Medical Center(哥伦比亚大学医学中心);John Hopkins University(约翰斯·霍普金斯大学)