检索结果-内蒙古大学图书馆

6th International Conference on intelligent Computing and Signal processing (ICSP)

作者： Tiantian Wang Xiaoqi Lu School of Information Engineering Inner Mongolia University of Science and Technology Baotou China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Baotou China Institute of Information Engineering Inner Mongolia University of Technology Hohhot China

DeepFakes blur the boundaries between reality and forgery, resulting in the collapse of exiting credit system, causing immeasurable consequences for national security and social order. Through analysis of existing face forgery techniques, it is found that most generation techniques rely on random noise distribution, and global information will be lost after up sampling. Therefore, we propose a deepfake detection algorithm based on improved MobileViT, which uses CNN local space biasing and the global space representation of the Transformer network to learn the local features and global representation of forged faces, respectively. Coordinate attention is introduced to obtain directional perception and position sensitive information, making the model locate synthetic traces of fake faces better and fusion local and global representation more effectively. For the improved generalization of the model, with the GELU activation function to solve the problem of neuron death. Our model achieved 96.2% on FF++(C23) datasets, and 93.7%,94.1%,96.3%,87.9% on DF, F2F, FS, and NT datasets, respectively. Comparing with previous methods, our model has shown detection robustness and better generalization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Label Words are Anchors: An information Flow Perspective for Understanding In-Context Learning

arXiv

引用

arXiv 2023年

作者： Wang, Lean Li, Lei Dai, Damai Chen, Deli Zhou, Hao Meng, Fandong Zhou, Jie Sun, Xu National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Pattern Recognition Center WeChat AI Tencent Inc. China

In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks. However, the underlying mechanism of how LLMs learn from the provided context remains under-explored. In this paper, we investigate the working mechanism of ICL through an information flow lens. Our findings reveal that label words in the demonstration examples function as anchors: (1) semantic information aggregates into label word representations during the shallow computation layers' processing;(2) the consolidated information in label words serves as a reference for LLMs' final predictions. Based on these insights, we introduce an anchor re-weighting method to improve ICL performance, a demonstration compression technique to expedite inference, and an analysis framework for diagnosing ICL errors in GPT2-XL. The promising applications of our findings again validate the uncovered ICL working mechanism and pave the way for future studies. © 2023, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time

arXiv

引用

arXiv 2024年

作者： Zhang, Mozhi Wang, Pengyu Tan, Chenkun Huang, Mianqiu Zhang, Dong Zhou, Yaqian Qiu, Xipeng School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential. Existing alignment techniques, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), typically embed predefined preferences directly within the model’s parameters. These methods, however, often result in a static alignment that can not account for the diversity of human preferences in practical applications. In response to this challenge, we propose an effective method, MetaAlign, which aims to help LLMs dynamically align with various explicit or implicit preferences specified at inference time. Experimental results show that LLMs optimized on our meticulously constructed MetaAlign Dataset can effectively align with any preferences specified at the inference stage, validating the feasibility of MetaAlign. We hope that our work can provide some insights into the alignment of language models. 1 Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Capsule Network for Speech Emotion recognition 1st

An Improved Capsule Network for Speech Emotion Recognition

引用

1st Southwest Data Science Conference, SDSC 2022

作者： Zhang, Huiyun Huang, Heming School of Computer Science Qinghai Normal University Xining China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining China

ISBN: (纸本)9783031233869

Speech Emotion recognition (SER) is an important research content in the field of speech recognition, and it can make Human-Computer Interaction (HCI) more natural and harmonious. At present, the research of SER faces such problems as data scarcity and overfitting. To tackle these problems, an Improve Capsule Network (I-CapsNet) using Data Augmentation (DA) technique is proposed for efficient SER task. Firstly, the model I-CapsNet is used to reduce the number of parameters and retain more texture and background information. It can also retain the angle and discriminative information of the entity, thereby to relieve the overfiting. Secondly, noise is used to augment the baseline datasets (EMODB, CASIA, and SAVEE) under five Signal-to-Noise Ratios (SNR), to solve the problem of data scarcity. Finally, an evaluation index EAI is defined to comprehensively analyze the performance of the model under different data division namely EIRD, EDRD, EICV, and EDCV. Compared to the previous research results, the model I-CapsNet has competitive performance on the corresponding augmented datasets. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Detecting DTI Using Graph Embedding and Multi-Head Attention Mechanism

Detecting DTI Using Graph Embedding and Multi-Head Attention...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xiaoli Chen, Yaoyu Yang, Wenli Yu, HaiPing Wu, Zimo Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan China China Graphics Society School of Information Wuhan Vocational College Professional Committee of Graphics and Big Data Wuhan China

ISBN: (纸本)9798350386226

Drug-target interaction (DTI) prediction has an important role in drug discovery, significantly expediting the drug design and development process. This paper proposes a new model, ERW-BiAN, that seamlessly integrates graph embedding representations with deep learning network. Specifically, we utilize an improved graph embedding model, ERW, to generate comprehensive feature vectors for each node within the knowledge graph. Subsequently, these feature vectors are fed into the BiAN model, which leverages an attention mechanism to assign precise weights to sequences. Experimental results demonstrate the superior accuracy and predictive prowess of ERW-BiAN in DTI prediction tasks. Furthermore, the case about COVID-19 shows that ERW-BiAN has the better application potential for predicting drug-target interactions. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Chinese Sentiment Analysis Model Incorporating Knowledge Graph and Deep Learning 7

A Chinese Sentiment Analysis Model Incorporating Knowledge G...

引用

7th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2023

作者： Zhao, Shengping Chen, Jinlong Qin, Xingguo School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9798350382877

With the rapid growth of social media and e-commerce, users are generating large amounts of textual review data on these platforms. Analyzing and mining these comment data is important for governments, enterprises, and consumers to make decisions. Therefore, sentiment analysis, especially for Chinese comments, has become an area of wide interest in industry and academia. Aiming at the characteristics of Chinese online reviews, this paper applies the techniques of knowledge graph and deep learning around sentence-level sentiment analysis and designs a sentiment analysis model that integrates different information such as sentiment knowledge graph and serialized annotation in a deep learning model to improve the accuracy and effectiveness of sentiment analysis of Chinese online reviews. This is important for improving products and services, understanding user needs, and making more informed business and policy decisions. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Fully Hyperbolic Rotation for Knowledge Graph Embedding 27

Fully Hyperbolic Rotation for Knowledge Graph Embedding

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Liang, Qiuyu Wang, Weihua Bao, Feilong Gao, Guanglai College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China

ISBN: (纸本)9781643685489

Hyperbolic rotation is commonly used to effectively model knowledge graphs and their inherent ***, existing hyperbolic rotation models rely on logarithmic and exponential mappings for feature *** models only project data features into hyperbolic space for rotation, limiting their ability to fully exploit the hyperbolic *** address this problem, we propose a novel fully hyperbolic model designed for knowledge graph *** of feature mappings, we define the model directly in hyperbolic space with the Lorentz *** model considers each relation in knowledge graphs as a Lorentz rotation from the head entity to the tail *** adopt the Lorentzian version distance as the scoring function for measuring the plausibility of *** results on standard knowledge graph completion benchmarks demonstrated that our model achieves competitive results with fewer *** addition, our model get the state-ofthe-art performance on datasets of CoDEx-s and CoDEx-m, which are more diverse and challenging than *** code is available at https://***/llqy123/FHRE. © 2024 The Authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Unilateral payoff control is infeasible in network attack-defense interactions

Unilateral payoff control is infeasible in network attack-de...

引用

2024 China Automation Congress, CAC 2024

作者： Zhao, Kaiwen Xia, Yu Su, Qi Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9798350368604

Network resilience generally refers to the ability of a network to maintain normal operation in the face of various failures and disturbances, which has many applications in social, financial, communication, and transportation systems. There is a large amount of research on designing strategies to disrupt the network from the perspective of attack and to protect the network from the defense standpoint. However, attacks and defenses in the real world often occur simultaneously and repeatedly. The study of network resilience should not be limited to the structural characteristics but should consider the functional characteristics of the network. We develop a general game-theoretic framework to study attack-defense repeated interactions on complex networks and examine the possibility of achieving precise control over the payoffs of attackers and defenders. Our findings reveal that neither the attacker nor the defender can unilaterally control their own payoff, the opponent’s payoff, or any linear combination thereof. This work highlights the limitations of unilateral payoff control in real-world interaction scenarios, a consideration often overlooked in numerous theoretical studies. © 2024 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Research on a rectangular microwave filter with rectangular groove

Research on a rectangular microwave filter with rectangular ...

引用

2022 International Symposium on Sensor Technology and Control, ISSTC 2022

作者： Qian, Jun Hou, Yifeng School of Electronic and Information Engineering Wuzhou University Wuzhou Guangxi China Guangxi Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Wuzhou Guangxi China

In this paper, a rectangular microwave filter with rectangular groove is designed. The filter adopts symmetrical three-stage structure. The first section is the slot line waveguide section to realize the input / output of microwave signal, the second section is the transition section, which adopts the impedance gradient structure, and the third section is the sspps section composed of periodic symmetrical rectangular groove and 90 degree bending structure. By adjusting the geometric size of the rectangular groove and its air gap, the passband width and stopband characteristics of the filter can be adjusted, and its microwave sub wavelength binding effect can be further improved, making the anti space electromagnetic interference ability of sspps filter more excellent. The filter can be applied to L ?s Band civil microwave communication system. © Published under licence by IOP Publishing Ltd.

关键词： Electromagnetic pulse

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Safety-Aware Scheduling of Real-Time Control Systems with Burst Tasks 22

Energy-Efficient Safety-Aware Scheduling of Real-Time Contro...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cheng, Ting Liang, Yonghui Xu, Qimin Zhu, Shanying Department of Automation Shanghai Jiao Tong University Shanghai 200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240 China

ISBN: (纸本)9798331527471

In industrial sites, multiple real-time control systems often share computing resources. However, burst computing tasks may lead to the random dropping of control computing subtasks, resulting in control failures and potential hazards. To address this issue, we propose an energy-efficient safety-aware task scheduling scheme based on mixed-integer programming. When burst computing tasks are triggered, this scheduling scheme adaptively releases resources from low-criticality control computing subtasks and adjusts the processor speed based on the dynamic voltage and frequency scaling technology (DVFS), ensuring the timely completion of burst computing tasks and keeping the control system state deviation within a safe threshold. To achieve the scheduling scheme, we propose an efficient algorithm called EESASA. Simulation results show that EESASA can minimize the overall cost of control and processor energy while ensuring the safety of the control system and the timely completion of burst computing tasks. © 2024 IEEE.

关键词： Dynamic frequency scaling

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：