检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yang, Yuting Huang, Pei Ma, Fei Fei Cao, Juan Zhang, Meishan Zhang, Jian Li, Jintao Key Lab Of Intelligent Information Processing Institute Of Computing Technology Chinese Academy Of Sciences Beijing100190 China University Of Chinese Academy Of Sciences Beijing100049 China Beijing100190 China Laboratory Of Parallel Software And Computational Science ISCAS Beijing100190 China China

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to evaluate word-level robustness. First, to study safe regions for a model, we introduce robustness radius which is the boundary where the model can resist any perturbation. As calculating the maximum robustness radius is computationally hard, we estimate its upper and lower bound. We repurpose attack methods as ways of seeking upper bound and design a pseudo-dynamic programming algorithm for a tighter upper bound. Then verification method is utilized for a lower bound. Further, for evaluating the robustness of regions outside a safe radius, we reexamine robustness from another view: quantification. A robustness metric with a rigorous statistical guarantee is introduced to measure the quantification of adversarial examples, which indicates the model's susceptibility to perturbations outside the safe radius. The metric helps us figure out why state-of-the-art models like BERT can be easily fooled by a few word substitutions, but generalize well in the presence of real-world noises. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

OpenAUC: towards AUC-oriented open-set recognition 22

OpenAUC: towards AUC-oriented open-set recognition

引用

Proceedings of the 36th International Conference on Neural information processing Systems

作者： Zitai Wang Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang SKLOIS Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University and SKLOIS Institute of Information Engineering CAS School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Traditional machine learning follows a close-set assumption that the training and test set share the same label space. While in many practical scenarios, it is inevitable that some test samples belong to unknown classes (open-set). To fix this issue, Open-Set Recognition (OSR), whose goal is to make correct predictions on both close-set samples and open-set samples, has attracted rising attention. In this direction, the vast majority of literature focuses on the pattern of open-set samples. However, how to evaluate model performance in this challenging task is still unsolved. In this paper, a systematic analysis reveals that most existing metrics are essentially inconsistent with the aforementioned goal of OSR: (1) For metrics extended from close-set classification, such as Open-set F-score, Youden's index, and Normalized Accuracy, a poor open-set prediction can escape from a low performance score with a superior close-set prediction. (2) Novelty detection AUC, which measures the ranking performance between close-set and open-set samples, ignores the close-set performance. To fix these issues, we propose a novel metric named OpenAUC. Compared with existing metrics, OpenAUC enjoys a concise pairwise formulation that evaluates open-set performance and close-set performance in a coupling manner. Further analysis shows that OpenAUC is free from the aforementioned inconsistency properties. Finally, an end-to-end learning method is proposed to minimize the OpenAUC risk, and the experimental results on popular benchmark datasets speak to its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CCA-Net: Zero-shot SSVEP classification via an integration of canonical correlation analysis and deep neural network

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Deng, Yang Ji, Zhiwei Wang, Yijun Zhou, S. Kevin Harbin Institute of Technology School of Life Science and Technology Heilongjiang Harbin 150001 China University of Science and Technology of China Division of Life Sciences and Medicine School of Biomedical Engineering Anhui Hefei 230026 China University of Science and Technology of China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research Jiangsu Suzhou 215123 China Nanjing Agricultural University College of Artificial Intelligence Jiangsu Nanjing 210095 China Chinese Academy of Sciences State Key Laboratory on Integrated Optoelectronics Institute of Semiconductors Beijing 100083 China University of Science and Technology of China Key Laboratory of Precision and Intelligent Chemistry Anhui Hefei 230026 China Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Beijing 100190 China

Accurate decoding of electroencephalographic (EEG) signals is a crucial foundation for brain-computer interface (BCI) applications. Among various decoding approaches, those that do not require calibration are particularly significant for advancing BCI technologies into everyday life, as they alleviate user fatigue by eliminating the need for user-specific training. In this study, we integrate a deep neural network with canonical correlation analysis (CCA) to form the CCA-Net approach for decoding steady-state visually evoked potential (SSVEP) based BCI without user-specific calibration, i.e., at the zero-shot scenario. The CCA-Net aims to reduce the cross-subject domain gap for better transfer learning and make full use of the testing signal itself. Specifically, it adapts the cross-subject dual-domain fusion network (CSDuDoFN) by transferring the global multi-reference least-squares transformation coefficient from source subjects to both source and target data to reduce the cross-subject domain gap. In addition, CCA-Net enhances the transfer template-based canonical correlation analysis (tt-CCA) by introducing a subject-specific template to replace the sine-cosine reference template and adding an extra CCA coefficient to make full use of the testing signal itself, resulting in the Modified tt-CCA. Finally, the features extracted by CSDuDoFN and Modified tt-CCA are integrated to produce the final decoding result. Our approach leverages the strengths of both data-driven and model-driven methods and achieves state-of-the-art performance on three publicly available datasets, thus holding the potential to facilitate everyday BCI applications based on SSVEP. The reproducibility code is available at: https://***/Sungden/Zero-shot-SSVEP-classification. © 1963-2012 IEEE.

关键词： Brain-computer interface (BCI) canonical correlation analysis (CCA) deep neural network (DNN) steady-state visual evoked potential (SSVEP) zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Notmetoo: An Autonomous Agent of Preventing Sexual Harassment and Crime

SSRN

引用

SSRN 2021年

作者： Qiaojuan, Huang Luo, Xudong Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Guangxi Key Lab of MultiSource Information Mining & Security School of Computer Science and Engineering Guangxi Normal University Guilin China

Nowadays more and more cars are around us, offering us great convenience in daily life. For example, Uber taxis in western countries and Didi taxis in China allow passengers to hail a ride anytime, anywhere, cheaper and convenient. However, many female passengers have been sexually harassed and even killed by evil taxi drivers in recent years. As a result, females are so afraid of taking a taxi out. Thus, in this paper, we develop an autonomous agent system to protect females (predominantly female passengers) from sexual Harassment and crime. Specifically, we first build the keyword library of criminal trends based on similar cases reported in the news. Then our system recognises a driver’s crime tendency through what the driver talks about with a female passenger. Once our system recognises a criminal tendency, it automatically takes the corresponding warning or makes distress calls to the police when necessary. Finally, we do many experiments to evaluate our system, showing that the system is effective in crime prevention. © 2021, The Authors. All rights reserved.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Staggered Grid Scheme for the FFT-Based Methods

引用

Chinese Journal of Electronics 2019年第5期28卷 1066-1072页

作者： XIE Jiaye KONG Weibin PANG Lili SONG Weiju HUANG Zhixiang WU Xianliang Industrial Center Nanjing Institute of Technology State Key Laboratory of Millimeter Waves College of Information Engineering Yancheng Institute of Technology Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University

A staggered grid scheme is proposed to reduce both the total memory requirement and the CPU time of generating the corrected near matrix in the FFTbased methods. Two sets of Cartesian grids are used to project the source points and the field points, *** proposed method does not lower the efficiency of computing far matrix-vector products, compared with the traditional uniform Cartesian grid scheme. Some numerical experiments are provided to demonstrate both the correctness and the efficiency of the proposed method.

关键词： Green’s function Singularity RFG-FFT Staggered grid scheme Corrected near matrix

来源：评论

学校读者我要写书评

暂无评论

High information Density and Low Coverage Data Storage in DNA with Efficient Channel Coding Schemes

arXiv

引用

arXiv 2024年

作者： Ding, Yi He, Xuan Nguyen, Tuan Thanh Song, Wentu Yakhini, Zohar Yaakobi, Eitan Pan, Linqiang Tang, Xiaohu Cai, Kui Information Coding and Transmission Key Lab of Sichuan Province Southwest Jiaotong University Sichuan Chengdu611756 China Cluster Singapore University of Technology and Design 487372 Singapore Faculty of Computer Science Technion - Israel Institute of Technology Haifa3200003 Israel School of Computer Science RUNI Herzliya4615200 Israel Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

DNA-based data storage has been attracting significant attention due to its extremely high data storage density, low power consumption, and long duration compared to conventional data storage media. Despite the recent advancements in DNA data storage technology, significant challenges remain. In particular, various types of errors can occur during the processes of DNA synthesis, storage, and sequencing, including substitution errors, insertion errors, and deletion errors. Furthermore, the entire oligo may be lost. In this work, we report a DNA-based data storage architecture that incorporates efficient channel coding schemes, including different types of error-correcting codes (ECCs) and constrained codes, for both the inner coding and outer coding for the DNA data storage channel. We also carried out large scale experiments to validate our proposed DNA-based data storage architecture. Specifically, 1.61 and 1.69 MB data were encoded into 30,000 oligos each, with information densities of 1.731 and 1.815, respectively. It has been found that the stored information can be fully recovered without any error at average coverages of 4.5 and 6.0, respectively. This experiment achieved the highest net information density and lowest coverage among existing DNA-based data storage experiments (with standard DNA), with data recovery rates and coverage approaching theoretical optima. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel coding

来源：评论

学校读者我要写书评

暂无评论

Adversarial Testing: A Novel On-Line Testing Method for Deep Learning Processors

Adversarial Testing: A Novel On-Line Testing Method for Deep...

引用

Asian Test Symposium (ATS)

作者： Wen Li Ying Wang Kaiwei Zou Huawei Li Xiaowei Li School of Computer and Information Technology Shanxi University Taiyuan Shanxi China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan Shanxi China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Electronic Engineering Tsinghua University Beijing China

Deep neural networks have shown outstanding performance on complex tasks. Recently, various researches have been developed to pursue fast and energy-efficient deep learning accelerators. However, devices may suffer from hard defects and hardware variability during its lifetime, which poses severe challenges to deep learning accelerators. To protect edge deep learning accelerators from fault-induced failures, we leverage the adversarial deep learning technique to tailor a lightweight online fault detection method for neural network accelerator chips. The proposed Adversarial Testing scheme (AT) is a function-level testing method outcompeting conventional test in several ways: negligible run-time overhead, super sensitivity to subtle hardware variations, which reduces chip over-kills and also the unnecessary diagnosis operations. The evaluation results show that AT can accurately detect fault occurrence and ensure the normal use of deep learning accelerator during its lifetime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OTKGE: multi-modal knowledge graph embeddings via optimal transport 22

OTKGE: multi-modal knowledge graph embeddings via optimal tr...

引用

Proceedings of the 36th International Conference on Neural information processing Systems

作者： Zongsheng Cao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang SKLOIS Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University and SKLOIS Institute of Information Engineering CAS School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Multi-modal knowledge graph embeddings (KGE) have caught more and more attention in learning representations of entities and relations for link prediction tasks. Different from previous uni-modal KGE approaches, multi-modal KGE can leverage expressive knowledge from a wealth of modalities (image, text, etc.), leading to more comprehensive representations of real-world entities. However, the critical challenge along this course lies in that the multi-modal embedding spaces are usually heterogeneous. In this sense, direct fusion will destroy the inherent spatial structure of different modal embeddings. To overcome this challenge, we revisit multi-modal KGE from a distributional alignment perspective and propose optimal transport knowledge graph embeddings (OTKGE). Specifically, we model the multi-modal fusion procedure as a transport plan moving different modal embeddings to a unified space by minimizing the Wasserstein distance between multi-modal distributions. Theoretically, we show that by minimizing the Wasserstein distance between the individual modalities and the unified embedding space, the final results are guaranteed to maintain consistency and comprehensiveness. Moreover, experimental results on well-established multi-modal knowledge graph completion benchmarks show that our OTKGE achieves state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Look one step ahead through first-order aggregation in reinforcement learning-based knowledge graph reasoning

引用

information Sciences 2025年 718卷

作者： Hao Wang Dandan Song Zhijing Wu YuHang Tian Jing Xu Laboratory of High-Volume Language Information Processing and Cloud Computing Beijing Lab of Intelligent Information Technology School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 Beijing China

Multi-hop reasoning is an effective and interpretable approach for query answering, as it finds reasoning paths over knowledge graphs (KGs) to enhance interpretability. Recent studies have applied reinforcement learning-based (RL-based) methods with policy agents to solve this problem. However, these methods primarily focus on sequential reasoning paths and candidate nodes, while overlooking the local structural information of adjacency subgraphs and the semantic correlations between relations at each decision step. In this paper, we propose a novel RL-based multi-hop reasoning model, L ook O ne S tep A head (LOSA), which leverages first-order aggregation to regard more expressive adjacency subgraphs rather than nodes as candidate actions and pays attention to the semantic correlations between relations. Specifically, an adjacency aggregation module encodes the local subgraph information and feeds the representations into the policy network to guide decision-making, thereby reducing backtracking and mitigating sparse-reward issues. Furthermore, a semantic matching module is designed to emphasize the semantic correlations of relations to improve the rationality of the reasoning paths. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed approach.

关键词： Knowledge graph completion Knowledge graph reasoning Link prediction Multi-hop reasoning

来源：评论

学校读者我要写书评

暂无评论

MVC-VPR: Mutual Learning of Viewpoint Classification and Visual Place Recognition

arXiv

引用

arXiv 2024年

作者： Gu, Qiwen Wang, Xufei Zhang, Fenglin Zhao, Junqiao Tao, Siyue Ye, Chen Feng, Tiantian Jiang, Changjun Department of Computer Science and Technology School of Electronics and Information Engineering Tongji University Shanghai China The Shanghai Research Institute for Intelligent Autonomous System Tongji University Shanghai China The MOE Key Lab of Embedded System and Service Computing Tongji University Shanghai China School of Surveying and Geo-Informatics Tongji University Shanghai China

Visual Place Recognition (VPR) aims to robustly identify locations by leveraging image retrieval based on descriptors encoded from environmental images. However, drastic appearance changes of images captured from different viewpoints at the same location pose incoherent supervision signals for descriptor learning, which severely hinder the performance of VPR. Previous work proposes classifying images based on manually defined rules or ground truth labels for viewpoints, followed by descriptor training based on the classification results. However, not all datasets have ground truth labels of viewpoints and manually defined rules may be suboptimal, leading to degraded descriptor performance. To address these challenges, we introduce the mutual learning of viewpoint self-classification and VPR. Starting from coarse classification based on geographical coordinates, we progress to finer classification of viewpoints using simple clustering techniques. The dataset is partitioned in an unsupervised manner while simultaneously training a descriptor extractor for place recognition. Experimental results show that this approach almost perfectly partitions the dataset based on viewpoints, thus achieving mutually reinforcing effects. Our method even excels state-of-the-art (SOTA) methods that partition datasets using ground truth labels. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：