中文
相关论文

相关论文: NeuRecover: Regression-Controlled Repair of Deep N…

200 篇论文

Systems based on Deep Neural Networks (DNNs) are increasingly being used in industry. In the process of system operation, DNNs need to be updated in order to improve their performance. When updating DNNs, systems used in companies that…

软件工程 · 计算机科学 2025-03-11 Takao Nakagawa , Susumu Tokumoto , Shogo Tokui , Fuyuki Ishikawa

The increasing use of deep neural networks (DNNs) in safety-critical systems has raised concerns about their potential for exhibiting ill-behaviors. While DNN verification and testing provide post hoc conclusions regarding unexpected…

机器学习 · 计算机科学 2023-05-09 Zhen Liang , Taoran Wu , Changyuan Zhao , Wanwei Liu , Bai Xue , Wenjing Yang , Ji Wang

Safety is a critical concern for the next generation of autonomy that is likely to rely heavily on deep neural networks for perception and control. Formally verifying the safety and robustness of well-trained DNNs and learning-enabled…

机器学习 · 计算机科学 2021-08-10 Xiaodong Yang , Tom Yamaguchi , Hoang-Dung Tran , Bardh Hoxha , Taylor T Johnson , Danil Prokhorov

Deep neural networks (DNNs) are being widely applied for various real-world applications across domains due to their high performance (e.g., high accuracy on image classification). Nevertheless, a well-trained DNN after deployment could…

机器学习 · 计算机科学 2020-11-20 Bing Yu , Hua Qi , Qing Guo , Felix Juefei-Xu , Xiaofei Xie , Lei Ma , Jianjun Zhao

As Deep Neural Networks (DNNs) are rapidly being adopted within large software systems, software developers are increasingly required to design, train, and deploy such models into the systems they develop. Consequently, testing and…

软件工程 · 计算机科学 2023-01-30 Jinhan Kim , Nargiz Humbatova , Gunel Jahangirova , Paolo Tonella , Shin Yoo

Neuron reconstruction is essential to generate exquisite neuron connectivity map for understanding brain function. Despite the significant amount of effect that has been made on automatic reconstruction methods, manual tracing by…

计算机视觉与模式识别 · 计算机科学 2020-03-20 Donghuan Lu , Sujun Zhao , Peng Xie , Kai Ma , Lijuan Liu , Yefeng Zheng

Deep neural networks (DNNs) are powerful learning machines that have enabled breakthroughs in several domains. In this work, we introduce a new retrospective loss to improve the training of deep neural network models by utilizing the prior…

计算机视觉与模式识别 · 计算机科学 2020-06-25 Surgan Jandial , Ayush Chopra , Mausoom Sarkar , Piyush Gupta , Balaji Krishnamurthy , Vineeth Balasubramanian

Deep neural networks (DNNs) are increasingly applied in safety-critical domains, such as self-driving cars, unmanned aircraft, and medical diagnosis. It is of fundamental importance to certify the safety of these DNNs, i.e. that they comply…

机器学习 · 计算机科学 2022-08-23 Fabian Bauer-Marquart , David Boetius , Stefan Leue , Christian Schilling

We present NNrepair, a constraint-based technique for repairing neural network classifiers. The technique aims to fix the logic of the network at an intermediate layer or at the last layer. NNrepair first uses fault localization to find…

机器学习 · 计算机科学 2021-06-16 Muhammad Usman , Divya Gopinath , Youcheng Sun , Yannic Noller , Corina Pasareanu

Deep neural networks (DNNs) have become increasingly popular in recent years. However, despite their many successes, DNNs may also err and produce incorrect and potentially fatal outputs in safety-critical settings, such as autonomous…

机器学习 · 计算机科学 2021-10-22 Idan Refaeli , Guy Katz

Deep neural networks (DNNs) have been found to be vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. While existing defense methods have demonstrated promising results, it is…

机器学习 · 计算机科学 2023-12-11 Yige Li , Xixiang Lyu , Xingjun Ma , Nodens Koren , Lingjuan Lyu , Bo Li , Yu-Gang Jiang

Deep neural networks (DNN) are growing in capability and applicability. Their effectiveness has led to their use in safety critical and autonomous systems, yet there is a dearth of cost-effective methods available for reasoning about the…

神经与进化计算 · 计算机科学 2019-08-22 David Shriver , Dong Xu , Sebastian Elbaum , Matthew B. Dwyer

Deep neural networks (DNNs) are increasingly being deployed in high-stakes applications, from self-driving cars to biometric authentication. However, their unpredictable and unreliable behaviors in real-world settings require new approaches…

密码学与安全 · 计算机科学 2025-10-01 Firas Ben Hmida , Abderrahmen Amich , Ata Kaboudi , Birhanu Eshete

The rapid and widespread adoption of Deep Neural Networks (DNNs) has called for ways to test their behaviour, and many testing approaches have successfully revealed misbehaviour of DNNs. However, it is relatively unclear what one can do to…

机器学习 · 计算机科学 2022-12-14 Jeongju Sohn , Sungmin Kang , Shin Yoo

Deep Neural Networks (DNNs) have grown in popularity over the past decade and are now being used in safety-critical domains such as aircraft collision avoidance. This has motivated a large number of techniques for finding unsafe behavior in…

机器学习 · 计算机科学 2021-04-27 Matthew Sotoudeh , Aditya V. Thakur

Deep neural networks (DNNs), trained with gradient-based optimization and backpropagation, are currently the primary tool in modern artificial intelligence, machine learning, and data science. In many applications, DNNs are trained offline,…

机器学习 · 计算机科学 2024-02-02 Jacob G. Elkins , Farbod Fahimi

Significant interest in applying Deep Neural Network (DNN) has fueled the need to support engineering of software that uses DNNs. Repairing software that uses DNNs is one such unmistakable SE need where automated tools could be beneficial;…

软件工程 · 计算机科学 2020-05-05 Md Johirul Islam , Rangeet Pan , Giang Nguyen , Hridesh Rajan

Over the past few years, deep neural networks (DNNs) have achieved tremendous success and have been continuously applied in many application domains. However, during the practical deployment in the industrial tasks, DNNs are found to be…

机器学习 · 计算机科学 2021-12-14 Hua Qi , Zhijie Wang , Qing Guo , Jianlang Chen , Felix Juefei-Xu , Lei Ma , Jianjun Zhao

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems. Recent works have shown the possibility of generating…

计算机视觉与模式识别 · 计算机科学 2018-12-21 Ziang Yan , Yiwen Guo , Changshui Zhang

The backpropagation algorithm remains the dominant and most successful method for training deep neural networks (DNNs). At the same time, training DNNs at scale comes at a significant computational cost and therefore a high carbon…

机器学习 · 计算机科学 2025-11-12 Sander Dalm , Joshua Offergeld , Nasir Ahmad , Marcel van Gerven
‹ 上一页 1 2 3 10 下一页 ›