FE-RNN: A fuzzy embedded recurrent neural network for improving interpretability of underlying neural network [PDF]
Information SciencesDeep learning enables effective predictions. But deep structures face some challenges on human interpretability compared to conventional techniques, e.g., fuzzy inference systems. It motivates more research works to alleviate the black box nature of deep
Chai Quek, Qi Cao
exaly +4 more sources
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks [PDF]
IEEE Transactions on Image Processing, 2020 IEEE Transactions on Image Processing (Accept).
Cuiling Lan, Jianru Xue, Pengfei Zhang
exaly +4 more sources
GR-RNN: Global-context residual recurrent neural networks for writer identification [PDF]
Pattern Recognition, 2021 To appear: Pattern ...
Sheng He, Lambert Schomaker
exaly +3 more sources
RNN-Test: Towards Adversarial Testing for Recurrent Neural Network Systems [PDF]
IEEE Transactions on Software Engineering, 2022 While massive efforts have been investigated in adversarial testing of convolutional neural networks (CNN), testing for recurrent neural networks (RNN) is still limited and leaves threats for vast sequential application domains. In this paper, we propose an adversarial testing framework RNN-Test for RNN systems, focusing on sequence-to-sequence ...
Jianmin Guo, Jiaguang Sun, Heyuan Shi
exaly +2 more sources
Related searches:
Tree-RNN: Tree structural recurrent neural network for network traffic classification
Expert Systems With Applications, 2021Abstract Network traffic classification plays an important role in network monitoring and network management. With the continuous development of network technology, traditional methods of traffic classification have more limitations in accuracy to deal with encrypted traffic.
Huaxi Gu, Wenting Wei
exaly +3 more sources
Cert-RNN: Towards Certifying the Robustness of Recurrent Neural Networks
Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 2021Certifiable robustness, the functionality of verifying whether the given region surrounding a data point admits any adversarial example, provides guaranteed security for neural networks deployed in adversarial environments. A plethora of work has been proposed to certify the robustness of feed-forward networks, e.g., FCNs and CNNs.
Tianyu Du +9 more
openaire +2 more sources
MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation [PDF]
IEEE Transactions on Knowledge and Data Engineering, 2020 Sequential recommendation is a fundamental task for network applications, and it usually suffers from the item cold start problem due to the insufficiency of user feedbacks. There are currently three kinds of popular approaches which are respectively based on matrix factorization (MF) of collaborative filtering, Markov chain (MC), and recurrent neural ...
Qiang Cui, Qiang Liu, Shu Wu
exaly +3 more sources
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network [PDF]
Physica D: Nonlinear Phenomena, 2020 43 pages, 10 figures, 78 ...
Alex Sherstinsky
exaly +4 more sources
RNN-Stega: Linguistic Steganography Based on Recurrent Neural Networks
IEEE Transactions on Information Forensics and Security, 2019Linguistic steganography based on text carrier auto-generation technology is a current topic with great promise and challenges. Limited by the text automatic generation technology or the corresponding text coding methods, the quality of the steganographic text generated by previous methods is inferior, which makes its imperceptibility unsatisfactory ...
Zhongliang Yang +4 more
openaire +1 more source