检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Dou, Shihan Liu, Yan Zhou, Enyu Gao, Songyang Li, Tianlong Xiong, Limao Zhao, Xin Jia, Haoxiang Ye, Junjie Zheng, Rui Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University Shanghai China Ant Group Shanghai China School of Computer Science Peking University Beijing China Institute of Modern Languages and Linguistics Fudan University Shanghai China Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Shanghai China

ISBN: (纸本)157735897X

The capability of the reward model (RM) is crucial for the success of Reinforcement Learning from Human Feedback (RLHF) in aligning with human preferences. However, as training progresses, the output space distribution of the policy model shifts. The RM, initially trained on responses sampled from the output distribution of the early policy model, gradually loses its ability to distinguish between responses from the newly shifted distribution. This issue is further compounded when the RM, trained on a specific data distribution, struggles to generalize to examples outside of that distribution. These two issues can be united as a challenge posed by the shifted distribution of the environment. To surmount this challenge, we introduce MetaRM, a novel method leveraging meta-learning to adapt the RM to the shifted environment distribution. MetaRM optimizes the RM in an alternating way, by preserving both the preferences of the original preference pairs, as well as maximizing discrimination power over new examples of the shifted distribution. Extensive experiments demonstrate that MetaRM can iteratively enhance the performance of human preference alignment by improving the RM’s capacity to identify subtle differences in samples of shifted distributions. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). 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

Linear-to-Circular Polarization Converter Based on Transmission Metamaterial 4

Linear-to-Circular Polarization Converter Based on Transmiss...

引用

4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021

作者： Li, Huixiang Wu, Xianliang Zhang, Liang Anhui University Key Laboratory of Intelligent Computing Signal Processing Hefei China Anhui Province Key Laboratory of Simulation and Design for Electronic Information Key Laboratory of Intelligent Computing Signal Processing Hefei Normal University Hefei China

ISBN: (纸本)9781733509619

A broadband transmissive linear-to-circular polarization conversion metamaterial composed of 5-layer '-shaped units was designed, and it was placed directly above the ordinary linear polarization antenna so that the antenna can radiate circular polarization waves. The 3dB axial ratio bandwidth is 11.5GHz-14.5GHz, and the relative axial ratio bandwidth reaches 23%, which proves that the polarization conversion surface has good polarization conversion characteristics. © 2021 Applied Computational Electromagnetics Society (ACES).

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

A Multi-level Approach to Learning Early Warning based on Cognitive Diagnosis and Learning Behaviors Analysis 26

A Multi-level Approach to Learning Early Warning based on Co...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Ma, Hua Zhao, Wen Jiang, Zixu Huang, Peiji Tang, Wensheng Zhang, Hongyu Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan Normal University College of Information Science and Engineering Changsha China Co. Ltd China Central South University School of Business Changsha China

ISBN: (纸本)9798350331684

Learning early warning is of great significance for coping with students' learning risks. The existing research fails in modeling the fluctuation of students' learning states and providing the multi-level early warning for students at different levels. To address them, a new approach of learning early warning is proposed to predict at-risk students in e-learning environment by combining cognitive diagnosis with learning behaviors analysis. In this approach, the students' learning process is modeled from four dimensions, i.e., learning quality, learning engagement, latent learning state, and historical learning performance. The convolutional neural network and long short-term memory network are used to explore the students' latent learning features. Then, the Adaboost algorithm is applied to predict students' learning performance. Based on the predicted performance, the evaluation rules are designed to provide multi-level learning early warning for students. Finally, the experiments demonstrate that the proposed method could predict at-risk students efficiently and accurately. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Ship Target Detection Method Based on Local Saliency Enhancement 5

Ship Target Detection Method Based on Local Saliency Enhance...

引用

5th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2022

作者： Li, Nana Pan, Xueli Yang, Lixia Huang, Zhixiang Wu, Zhenhua Zhang, Xianqi Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Hefei China Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei China East China Institute of Optoelectronic Integrated Devices Suzhou China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

Due to the non-uniformity of ship target scattering, speckle noises and side lobes, synthetic aperture radar (SAR) ship target detection is facing great challenges. Therefore, to improve the detection performance in this scenario, the ship detection method based on the local saliency enhancement is proposed in this paper. Firstly, the proposed method improves the target-to-clutter ratio (TCR) by combining the relative differences of multi-features between ship target and the clutter background, and the threshold segmentation is performed based on the final local enhancement results. The experimental results show that the proposed method can suppress clutter background and speckle noises, improve the TCR and the algorithm has a high detection rate and a low false alarm rate in the complex background and multi-target marine environment. © 2022 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Preprocessed GMRES for fast solution of linear equations

arXiv

引用

arXiv 2024年

作者： Zhang, Juan Luo, Yiyi Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University China

The article mainly introduces preprocessing algorithms for solving linear equation systems. This algorithm uses three algorithms as inner iterations, namely RPCG algorithm, ADI algorithm, and Kaczmarz algorithm. Then, it uses BA-GMRES as an outer iteration to solve the linear equation system. These three algorithms can indirectly generate preprocessing matrices, which are used for solving equation systems. In addition, we provide corresponding convergence analysis and numerical examples. Through numerical examples, we demonstrate the effectiveness and feasibility of these preprocessing methods. Furthermore, in the Kaczmarz algorithm, we introduce both constant step size and adaptive step size, and extend the parameter range of the Kaczmarz algorithm to α ∈ (0, ∞). We also study the solution rate of linear equation systems using different step sizes. Numerical examples show that both constant step size and adaptive step size have higher solution efficiency than the solving algorithm without preprocessing. © 2024, CC BY.

关键词： Linear equations

来源：评论

学校读者我要写书评

暂无评论

A Transformer-based Neural Architecture Search Method

arXiv

引用

arXiv 2025年

作者： Wang, Shang Tang, Huanrong Ouyang, Jianquan Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Computer Science School of Cyberspace Security Xiangtan University Hunan Xiangtan China

This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network structures with better translation results, we considered perplexity as an auxiliary evaluation metric for the algorithm in addition to BLEU scores and iteratively improved each individual neural network within the population by a multi-objective genetic algorithm. Experimental results show that the neural network structures searched by the algorithm outperform all the baseline models, and that the introduction of the auxiliary evaluation metric can find better models than considering only the BLEU score as an evaluation metric. © 2025, CC BY.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

COMPLEX-VALUED CROSS-DOMAIN FEW-SHOT LEARNING NETWORK FOR POLSAR IMAGE CLASSIFICATION

COMPLEX-VALUED CROSS-DOMAIN FEW-SHOT LEARNING NETWORK FOR PO...

引用

IET International Radar Conference 2023, IRC 2023

作者： Cao, Yice Zhu, Dayi Wu, Zhenhua Chen, Jie Huang, Zhixiang Yang, Lixia Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electronics and Information Engineering Anhui University Hefei230601 China 38th Research Institute China Electronics Technology Group Corporation Hefei230088 China

ISBN: (纸本)9781839539954

Gathering reliable labeled samples for polarimetric synthetic aperture (PolSAR) image classification is laborious. Moreover, applying a trained classifier to new domains often leads to noticeable performance degradation due to domain disparities. Therefore, this paper proposes the novel complex-valued cross-domain (CD) few-shot learning classification (CCFSLC) method for PolSAR images to address these issues. Firstly, the transferrable knowledge learning module (TKLM) with a complex-valued feature encoder (CVFE) is trained using source data with sufficient labeled samples. Then, the deep few-shot learning module (DFSLM), constructed using the pre-trained CVFE, is trained by episodes in both source and target domains, with only minimal target labeled samples. Meanwhile, the adversarial domain adaptation module (ADAM) is employed to eliminate domain shift. The proposed CCFSLC mainly focuses on exploring discriminative information from raw PolSAR data, while reducing the domain gap to recognize novel categories in unseen domains with only a few annotated samples. Experiments on typical PolSAR datasets validate the effectiveness of the proposed method. © The Institution of Engineering & Technology 2023.

关键词： Polarimeters

来源：评论

学校读者我要写书评

暂无评论

A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture

arXiv

引用

arXiv 2025年

This paper proposes a neural architecture search space using ResNet as a framework, with search objectives including parameters for convolution, pooling, fully connected layers, and connectivity of the residual network. In addition to recognition accuracy, this paper uses the loss value on the validation set as a secondary objective for optimization. The experimental results demonstrate that the search space of this paper together with the optimisation approach can find competitive network architectures on the MNIST, Fashion-MNIST and CIFAR100 datasets. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On book thickness parameterized by the vertex cover number

引用

Science China(information Sciences) 2022年第4期65卷 112-113页

作者： Yunlong LIU Jie CHEN Jingui HUANG School of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University

Dear editor,Book thickness for graphs forms a major theme in graph theory and has a broad application in the fields of sorting permutations, fault tolerant VLSI design, parallel computing, and others. The book Thickness problem, even if the vertex order is taken as part of the input, was shown to be NP-complete in general [1, 2]. Just because of this, parameterized algorithms have been proposed to deal with it [3].

关键词： Book Thickness Vertex Cover Number Linear Order 1-page embedding graph kernel

来源：评论

学校读者我要写书评

暂无评论

Heterophilic Graph Representation Learning Based on Multi-Order information Extraction and High and Low Pass Filters 10

Heterophilic Graph Representation Learning Based on Multi-Or...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Wu, Ling Li, Xinyu Yang, Yingjie Guo, Kun Zhang, Qishan Fuzhou University College of Computer and Data Science Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing China De Montfort University School of Computer Science and Informatics Leicester United Kingdom Shanghai International Studies University College of Economics and Humanities Shanghai China

ISBN: (纸本)9798331520861

Real-world networks can be divided into homophilic and heterophilic graphs. Significantly, many nodes tend to be heterophilic in a homophilic graph. Graph representation learning in heterophilic graphs has attracted considerable significance in recent years as it breaks the homophily assumption and achieves higher-quality graph embeddings. However, existing heterophilic graph representation learning methods often mix attribute and topological information, neglecting the mutual exclusion between attribute information and topological information. Furthermore, algorithms in heterogeneous graphs usually rely on specific matrix structures to capture high-order information, which may restrict the applicability of these methods. To tackle these issues, this paper proposes a GNN-based strategy for Heterophilic graph Representation Learning based on Multi-order information extraction and High and Low pass filters (HRLMHL). First, we designed two relatively independent modules to learn attribute information and topological information, respectively, to address the issue of mismatch. Second, we built a multi-order information extraction module to extract multi-order similarity features, thereby achieving the learning of high-order graph information. Experiments on real datasets show that the node classification accuracy is superior to that of the state-of-the-art methods on most datasets. © 2024 IEEE.

关键词： Contrastive 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：