中文
相关论文

相关论文: NAPER: Fault Protection for Real-Time Resource-Con…

200 篇论文

Nowadays, the extensive exploitation of Deep Neural Networks (DNNs) in safety-critical applications raises new reliability concerns. In practice, methods for fault injection by emulation in hardware are efficient and widely used to study…

机器学习 · 计算机科学 2023-06-01 Mahdi Taheri , Mohammad Hasan Ahmadilivani , Maksim Jenihhin , Masoud Daneshtalab , Jaan Raik

Deep Neural Networks (DNNs) are widely employed in safety-critical domains, where ensuring their reliability is essential. Triple Modular Redundancy (TMR) is an effective technique to enhance the reliability of DNNs in the presence of…

机器学习 · 计算机科学 2025-07-15 Kimia Soroush , Nastaran Shirazi , Mohsen Raji

Because deep neural networks (DNNs) rely on a large number of parameters and computations, their implementation in energy-constrained systems is challenging. In this paper, we investigate the solution of reducing the supply voltage of the…

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

The adoption of deep neural networks (DNNs) in safety-critical domains has engendered serious reliability concerns. A prominent example is hardware transient faults that are growing in frequency due to the progressive technology scaling,…

机器学习 · 计算机科学 2021-03-30 Zitao Chen , Guanpeng Li , Karthik Pattabiraman

Despite its maturity, the field of fault-tolerant redundancy suffers from significant terminological fragmentation, where functionally equivalent methods are frequently described under disparate names across academic and industrial domains.…

系统与控制 · 电气工程与系统科学 2026-03-17 Lukas Flad , Mark Leyer , Felix Sebastian Nitz , Tobias Krawutschke

Convolutional Neural Networks (CNNs) have become integral in safety-critical applications, thus raising concerns about their fault tolerance. Conventional hardware-dependent fault tolerance methods, such as Triple Modular Redundancy (TMR),…

Deep neural networks (DNNs) have become ubiquitous in machine learning, but their energy consumption remains problematically high. An effective strategy for reducing such consumption is supply-voltage reduction, but if done too…

机器学习 · 计算机科学 2024-12-13 Hao-Lun Sun , Lei Hsiung , Nandhini Chandramoorthy , Pin-Yu Chen , Tsung-Yi Ho

Deep neural networks (DNNs) have become ubiquitous thanks to their remarkable ability to model complex patterns across various domains such as computer vision, speech recognition, robotics, etc. While large DNN models are often more…

机器学习 · 计算机科学 2025-11-18 Omkar Shende , Gayathri Ananthanarayanan , Marcello Traiola

The last decade has witnessed the breakthrough of deep neural networks (DNNs) in many fields. With the increasing depth of DNNs, hundreds of millions of multiply-and-accumulate (MAC) operations need to be executed. To accelerate such…

硬件体系结构 · 计算机科学 2022-11-29 Amro Eldebiky , Grace Li Zhang , Georg Boecherer , Bing Li , Ulf Schlichtmann

Deep neural networks (DNNs) have been widely applied to solve real-world regression problems. However, selecting optimal network structures remains a significant challenge. This study addresses this issue by linking neuron selection in DNNs…

统计计算 · 统计学 2025-09-30 Noah Yi-Ting Hung , Li-Hsiang Lin , Vince D. Calhoun

The superior performance of Deep Neural Networks (DNNs) has led to their application in various aspects of human life. Safety-critical applications are no exception and impose rigorous reliability requirements on DNNs. Quantized Neural…

机器学习 · 计算机科学 2023-06-19 Mohammad Hasan Ahmadilivani , Mahdi Taheri , Jaan Raik , Masoud Daneshtalab , Maksim Jenihhin

Deep neural networks (DNNs) have been shown to tolerate "brain damage": cumulative changes to the network's parameters (e.g., pruning, numerical perturbations) typically result in a graceful degradation of classification accuracy. However,…

密码学与安全 · 计算机科学 2019-06-05 Sanghyun Hong , Pietro Frigo , Yiğitcan Kaya , Cristiano Giuffrida , Tudor Dumitraş

Systematic techniques to improve quality of deep neural networks (DNNs) are critical given the increasing demand for practical applications including safety-critical ones. The key challenge comes from the little controllability in updating…

An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans. Effective deployment of DNNs in these interactive scenarios requires meeting…

性能 · 计算机科学 2024-07-09 Chengcheng Wan , Muhammad Santriaji , Eri Rogers , Henry Hoffmann , Michael Maire , Shan Lu

With the widespread deployment of deep neural networks (DNNs), ensuring the reliability of DNN-based systems is of great importance. Serious reliability issues such as system failures can be caused by numerical defects, one of the most…

软件工程 · 计算机科学 2023-04-25 Linyi Li , Yuhao Zhang , Luyao Ren , Yingfei Xiong , Tao Xie

Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability.We propose the fault sneaking attack on DNNs,…

机器学习 · 计算机科学 2025-07-08 Pu Zhao , Siyue Wang , Cheng Gongye , Yanzhi Wang , Yunsi Fei , Xue Lin

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from…

机器学习 · 计算机科学 2020-10-20 Francesco Crecchi , Marco Melis , Angelo Sotgiu , Davide Bacciu , Battista Biggio

Humans excel at lifelong learning, as the brain has evolved to be robust to distribution shifts and noise in our ever-changing environment. Deep neural networks (DNNs), however, exhibit catastrophic forgetting and the learned…

机器学习 · 计算机科学 2023-02-23 Fahad Sarfraz , Elahe Arani , Bahram Zonooz

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements.…

机器学习 · 计算机科学 2020-11-12 Ussama Zahid , Giulio Gambardella , Nicholas J. Fraser , Michaela Blott , Kees Vissers
‹ 上一页 1 2 3 10 下一页 ›