The complexity of neural networks however makes it difficult to explain the whole decision process used by the model, which makes understanding deep learning models an active research topic. In this work we address this issue by extracting the knowledge acquired by trained Deep Neural Networks (...
K. Simonyan, A. V edaldi, and A. Zisserman. Deep insideconvolutional networks: Visualising image classification models and saliency maps. InWorkshop Proc. ICLR, 2014. P. M. Rasmussen, T. Schmah, K. H. Madsen, T. E. Lund, S. C. Strother, and L. K. Hansen. Visualization of nonl...
Thus, criteria able to stably and significantly reduce the computational complexity of deep neural networks across applications are relevant for practitioners. In this paper, we propose a novel pruning framework based on Layer-wise Relevance Propagation (LRP) [7]. LRP was originally developed as an...
We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Specifically, we show that we can decompose the pre-activation prediction of a neural network into a linear combi...
DxNA T - Deep Neural Networks for Explaining Non-Recurring Traffic Congestion 深度神经网络解释非经常性交通堵塞 非经常性交通挤塞是由临时交通中断所引起,例如意外、运动会、恶劣天气等。我们使用实时交通速度、拥堵因素(交通拥堵指标)和一年多以来在田纳西州纳什维尔收集的事件相关数据来训练多层深度神经网络。流量...
Indeed, it constitutes one of the oldest and most prominent explanation technologies for machine learning models with relevance for both, deep and shallow networks. A huge number of measures have been proposed such as mutual information, permutation feature importance, deep lift, LIME, GMLVQ, or ...
This is the official repository for paper "Explaining Deep Convolutional Neural Networks via Unsupervised Visual-Semantic Filter Attention" to appear in CVPR 2022. Authors: Yu Yang, Seungbae Kim, Jungseock Joo Datasets Common Objects in Context (COCO) Please follow the instructions in the COCO API...
Deep neural networks are the most sophisticated approach that can be used to address the limitations of matrix factorization. It allows for modeling the nonlinear interactions in the data and finding hidden patterns in the data that couldn’t otherwise be discovered. Neural networks architecture ...
Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks. NIPS'19 Deep Learning based Vulnerability Detection: Are We There Yet? TSE’20 但由于神经网络属于黑盒模型,安全专家也无法了解其决策过程,导致此类方法难以在实际场景中应用。目前在AI领域已有一...
A Deep Learning-based Fine-grained Hierarchical Learning Approach for Robust Malware Classification. arXiv'20NF-GNN:Network Flow Graph Neural Networks for Malware Detection and Classification. (不是CFG) 本文提出CFGExpaliner,是首个针对基于GNN进行恶意软件分类(注意不是检测)的可解释性工作。CFGExplainer在...