Results 61 to 70 of about 215,342 (268)

Decentralized Adversarial Training Over Graphs

IEEE Transactions on Information Theory
arXiv admin note: text overlap with arXiv:2303 ...
Ying Cao, Elsa Rizk, Stefan Vlaski, Ali H. Sayed   +3 more
openaire   +2 more sources

Strength-Adaptive Adversarial Training

, 2022
Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness ...
Yu, Chaojian, Zhou, Dawei, Shen, Li, Yu, Jun, Han, Bo, Gong, Mingming, Wang, Nannan, Liu, Tongliang   +7 more
openaire   +2 more sources

Continual Learning for Multimodal Data Fusion of a Soft Gripper

Advanced Robotics Research, EarlyView.
Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley   +1 more source

CellPolaris: Transfer Learning for Gene Regulatory Network Construction to Guide Cell State Transitions

Advanced Science, EarlyView.
CellPolaris decodes how transcription factors guide cell fate by building gene regulatory networks from transcriptomic data using transfer learning. It generates tissue‐ and cell‐type‐specific networks, identifies master regulators in cell state transitions, and simulates TF perturbations in developmental processes.
Guihai Feng, Xin Qin, Jiahao Zhang, Wuliang Huang, Yiyang Zhang, Wentao Cui, Yao Chen, Shirui Li, Wenhao Liu, Yao Tian, Yana Liu, Jingxi Dong, Ping Xu, Zhenpeng Man, Guole Liu, Zhongming Liang, Xinlong Jiang, Xiaodong Yang, Pengfei Wang, Ge Yang, Hongmei Wang, Xuezhi Wang, Ming‐Han Tong, Yuanchun Zhou, Shihua Zhang, Yiqiang Chen, Yong Wang, Xin Li   +27 more
wiley   +1 more source

Phase-shifted Adversarial Training

, 2023
Adversarial training has been considered an imperative component for safely deploying neural network-based applications to the real world. To achieve stronger robustness, existing methods primarily focus on how to generate strong attacks by increasing the number of update steps, regularizing the models with the smoothed loss function, and injecting the
Kim, Yeachan, Kim, Seongyeon, Seo, Ihyeok, Shin, Bonggun   +3 more
openaire   +2 more sources

Unpaired Learning‐Enabled Nanotube Identification from AFM Images

Advanced Science, EarlyView.
Identifying nanotubes on rough substrates is notoriously challenging for conventional image analysis. This work presents an unpaired deep learning approach that automatically extracts nanotube networks from atomic force microscopy images, even on complex polymeric surfaces used in roll‐to‐roll printing.
Soyoung Na, Soobin Park, Younsu Jung, Jinhwa Park, Jimin Hong, Jihyun Lee, Albert Kim, Bongjun Kim, Gyoujin Cho, Eunju Cha, Seung Hyun Song   +10 more
wiley   +1 more source

Diffusion‐MRI‐Based Estimation of Cortical Architecture via Machine Learning (DECAM) in Primate Brains

Advanced Science, EarlyView.
We present Diffusion‐MRI‐based Estimation of Cortical Architecture via Machine Learning (DECAM), a deep‐learning framework for estimating primate brain cortical architecture optimized with best response constraint and cortical label vectors. Trained using macaque brain high‐resolution multi‐shell dMRI and histology data, DECAM generates high‐fidelity ...
Tianjia Zhu, Minhui Ouyang, Shufang Tan, Jianlin Guo, Ziqin Zhang, Xuan Liu, Risheng Liu, Hao Huang   +7 more
wiley   +1 more source

Adversarial examples defense method based on multi-dimensional feature maps knowledge distillation

网络与信息安全学报, 2022
The neural network approach has been commonly used in computer vision tasks.However, adversarial examples are able to make a neural network generate a false prediction.Adversarial training has been shown to be an effective approach to defend against the ...
Baolin QIU, Ping YI
doaj   +1 more source

Adversarial Example Detection and Classification With Asymmetrical Adversarial Training

, 2020
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
Kolouri, Soheil, Rohde, Gustavo K., Yin, Xuwang   +2 more
core  

Harnessing Time‐Dependent Magnetic Texture Dynamics via Spin‐Orbit Torque for Physics‐Enhanced Neuromorphic Computing

Advanced Science, EarlyView.
A neuromorphic computing platform using spin‐orbit torque‐controlled magnetic textures is reported. The device implements bio‐inspired synaptic functions and achieves high performance in both pattern recognition (>93%) and combinatorial optimization (>95%), enabling unified processing of cognitive and optimization tasks.
Yifan Zhang, Yu Li, Huai Lin, Xinying Wang, Long Liu, Guoliang Xing, Di Wang, Zhihao Zhao, Zhipeng Guo, Junbo Yang, Jiebin Niu, Yan Sun, Tom Wu, Guozhong Xing   +13 more
wiley   +1 more source