检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhao, Haiquan Li, Lingyu Chen, Shisong Kong, Shuqi Wang, Jiaan Huang, Kexin Gu, Tianle Wang, Yixu Wang, Jian Liang, Dandan Li, Zhixu Teng, Yan Xiao, Yanghua Wang, Yingchun Shanghai Artificial Intelligence Laboratory China School of Computer Science Fudan University China School of Information Renmin University of China China Renmin University of China China

ISBN: (纸本)9798891761643

Emotion Support Conversation (ESC) is a crucial application, which aims to reduce human stress, offer emotional guidance, and ultimately enhance human mental and physical well-being. With the advancement of Large Language Models (LLMs), many researchers have employed LLMs as the ESC models. However, the evaluation of these LLM-based ESCs remains uncertain. Inspired by the awesome development of role-playing agents, we propose an ESC Evaluation framework (i.e., ESC-Eval), which uses a role-playing agent to interact with ESC models, followed by a manual evaluation of the interactive dialogues. In detail, we first reorganize 2,801 role-playing cards from seven existing datasets to define the roles of the role-playing agent. Second, we train a specific role-playing model - ESC-Role to mimic the behavior of a real person experiencing distress. Third, through ESC-Role and organized role cards, we systematically conduct experiments using 14 LLMs as the ESC models, including general AI-assistant LLMs (e.g., ChatGPT) and ESC-oriented LLMs (e.g., ExTES-Llama). We conduct comprehensive human annotations on interactive multi-turn dialogues of different ESC models. The results show that ESC-oriented LLMs exhibit superior ESC abilities compared to general AI-assistant LLMs, but there is still a gap behind human performance. Moreover, to automate the evaluation of future ESC models, we developed ESC-RANK, which trained on the annotated data, achieving a scoring performance surpassing 35 points of GPT-4. Our data and code are available at https://***/haidequanbu/ESC-Eval. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Attention-stacking adaptive fuzzy neural networks for autism diagnosis

Attention-stacking adaptive fuzzy neural networks for autism...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Shuzhan Xiao, Lei Huang, Hui Hu, Zhongyi Wenzhou University Institute of Intelligent Information System Wenzhou University Key Laboratory of Intelligent Image Processing and Analysis College of Computer Science and Artificial Intelligence Wenzhou China

ISBN: (纸本)9798350386226

The current diagnostic methods for Autism Spectrum Disorder (ASD) based on Resting-State Functional Magnetic Resonance Imaging (rs-fMRI) face two significant challenges. Firstly, the functional connectivity networks (FCNs) of the brain are subject to uncertainty due to noise interference during the rs-fMRI acquisition process. Secondly, variations in equipment parameters across different imaging sites lead to diverse distributions of collected features. To address these issues, this paper introduces a novel Multi-Task Stacked Adaptive Fuzzy Neural Network (AT-STTSK) specifically designed for Autism Spectrum Disorder (ASD) classification. The proposed network seamlessly integrates a Multi-Output TSK (MO-TSK) fuzzy system, a Stacked Autoencoder (SAE), and a Transformer. This integration aims to reduce the impact of uncertainty factors, enhance the model's interpretability, and leverage the multi-head attention mechanisms to capture both local and global information, thus strengthening feature learning. Additionally, we explore the utilization of a Contrastive Learning (CL) strategy to further optimize the model. By incorporating these advancements, our AT-STTSK network offers a promising approach for improving the accuracy and reliability of ASD diagnosis based on rs-fMRI data. The validity of the method in this paper is verified on ABIDE dataset, and the result shows that the accuracy rate can reach 85.7% at most. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Enhancing Adversarial Robustness in SNNs with Sparse Gradients 41

Enhancing Adversarial Robustness in SNNs with Sparse Gradien...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Yujia Bu, Tong Ding, Jianhao Hao, Zecheng Huang, Tiejun Yu, Zhaofei NERCVT School of Computer Science Peking University China National Key Laboratory for Multimedia Information Processing Peking University China School of Computer Science Peking University China Institution for Artificial Intelligence Peking University China

Spiking Neural Networks (SNNs) have attracted great attention for their energy-efficient operations and biologically inspired structures, offering potential advantages over artificial Neural Networks (ANNs) in terms of energy efficiency and interpretability. Nonetheless, similar to ANNs, the robustness of SNNs remains a challenge, especially when facing adversarial attacks. Existing techniques, whether adapted from ANNs or specifically designed for SNNs, exhibit limitations in training SNNs or defending against strong attacks. In this paper, we propose a novel approach to enhance the robustness of SNNs through gradient sparsity regularization. We observe that SNNs exhibit greater resilience to random perturbations compared to adversarial perturbations, even at larger scales. Motivated by this, we aim to narrow the gap between SNNs under adversarial and random perturbations, thereby improving their overall robustness. To achieve this, we theoretically prove that this performance gap is upper bounded by the gradient sparsity of the probability associated with the true label concerning the input image, laying the groundwork for a practical strategy to train robust SNNs by regularizing the gradient sparsity. We validate the effectiveness of our approach through extensive experiments on both image-based and event-based datasets. The results demonstrate notable improvements in the robustness of SNNs. Our work highlights the importance of gradient sparsity in SNNs and its role in enhancing robustness. Copyright 2024 by the author(s)

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine intelligence 2025年第7期47卷 5475-5488页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing101408 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 314100 China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic-like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. First, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic-like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. © 1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Pruning Networks With Cross-Layer Ranking & k-Reciprocal Nearest Filters

引用

IEEE Transactions on Neural Networks and Learning Systems 2023年第11期34卷 9139-9148页

作者： Lin, Mingbao Cao, Liujuan Zhang, Yuxin Shao, Ling Lin, Chia-Wen Ji, Rongrong School of Informatics Xiamen University Media Analytics and Computing Laboratory Department of Artificial Intelligence Xiamen361005 China Tencent Youtu Laboratory Shanghai200233 China School of Informatics Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City Computer Science Department Xiamen361005 China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates National Tsing Hua University Department of Electrical Engineering and the Institute of Communications Engineering Hsinchu30013 Taiwan Institute of Artificial Intelligence Xiamen University Xiamen361005 China

This article focuses on filter-level network pruning. A novel pruning method, termed CLR-RNF, is proposed. We first reveal a 'long-tail' pruning problem in magnitude-based weight pruning methods and then propose a computation-aware measurement for individual weight importance, followed by a cross-layer ranking (CLR) of weights to identify and remove the bottom-ranked weights. Consequently, the per-layer sparsity makes up the pruned network structure in our filter pruning. Then, we introduce a recommendation-based filter selection scheme where each filter recommends a group of its closest filters. To pick the preserved filters from these recommended groups, we further devise a ${k}$ -reciprocal nearest filter (RNF) selection scheme where the selected filters fall into the intersection of these recommended groups. Both our pruned network structure and the filter selection are nonlearning processes, which, thus, significantly reduces the pruning complexity and differentiates our method from existing works. We conduct image classification on CIFAR-10 and ImageNet to demonstrate the superiority of our CLR-RNF over the state-of-the-arts. For example, on CIFAR-10, CLR-RNF removes 74.1% FLOPs and 95.0% parameters from VGGNet-16 with even 0.3% accuracy improvements. On ImageNet, it removes 70.2% FLOPs and 64.8% parameters from ResNet-50 with only 1.7% top-five accuracy drops. Our project is available at https://***/lmbxμCLR-RNF. © 2012 IEEE.

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Recipe Retrieval With Fine-Grained Prompting Alignment and Evidential Semantic Consistency

引用

IEEE Transactions on Multimedia 2025年 27卷 2783-2794页

作者： Huang, Xu Liu, Jin Zhang, Zhizhong Xie, Yuan Tang, Yongqiang Zhang, Wensheng Cui, Xiaohui Wuhan University School of Computer Science Wuhan430072 China Ministry of Education Wuhan430062 China East China Normal University School of Computer Science and Technology Shanghai200062 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China

Alignment between the food images and the corresponding recipes is an emerging cross-modal representation learning task. In this task, the recipes are composed of three components, i.e., food title, ingredient lists, and cooking instructions, which require a fine-grained alignment between the features of the two modalities. Existing methods usually aggregate the recipes into global embeddings and then align them with the global image embeddings. Meanwhile, semantic classification is frequently used in these methods to regularize the embeddings of the two modalities. While these methods are efficient, there remain two problems. (1) Forcing the alignment between the global images and recipes embeddings may result in losing the component-specific information. (2) The high diversity of food appearance leads to high uncertainty in the semantic classification of food images and recipes. To solve these problems, we propose a Fine-grained Prompting and Alignment (FPA) model to enhance the feature extraction and bring more component-specific information for fine-grained alignment. Furthermore, to regularize the semantic information contained in the cross-modal features, we design an Evidential Semantic Consistency (ESC) loss to keep the cross-modal semantic consistency. We have conducted comprehensive experiments on the benchmark dataset Recipe1M and the state-of-the-art results on the cross-modal recipe retrieval task demonstrate the effectiveness of our method. © 1999-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Cognitive Presence in Online Collaborative Learning Discussions Using Knowledge Information 4

Automatic Detection of Cognitive Presence in Online Collabor...

引用

4th International Conference on Educational Technology, ICET 2024

作者： Luo, Sheng Ye, Junmin Yu, Shuang Yin, Xinghan Ren, Wen Si, Kaiyan Zhao, Gang Central China Normal University School of Computer Science Hubei China Central China Normal University Faculty of Artificial Intelligence Education Hubei China Central China Normal University School of Computer Science Wuhan China Central China Normal University Hubei Key Laboratory of Digital Education Faculty of Artificial Intelligence In Education Wuhan China

ISBN: (纸本)9798350376944

Learners' cognition is crucial in online collaborative learning, and cognitive presence is an important indicator of cognition. Therefore, how to automatically detect cognitive presence in student discussions is a hot topic in current research. However, existing studies have not considered the knowledge information in collaborative learning discussions, which is relevant to students' cognition. Based on this, this study proposed an automatic detection approach that utilizes knowledge information and deep learning models to automatically detect cognitive presence in student discussions. We conducted our experiments on a dataset containing 8795 pieces of data. The experimental results show that the proposed model achieves an accuracy of 77.63%, which outperforms all baseline models. Our work provides an accurate and efficient tool for automatically analyzing cognitive presence and helps teachers implement interventions. © 2024 IEEE.

关键词： Collaborative learning

来源：评论

学校读者我要写书评

暂无评论

PM2.5 concentration prediction model based on SA-LSTM

PM2.5 concentration prediction model based on SA-LSTM

引用

2023 International Conference on artificial intelligence, Systems and Network Security, AISNS 2023

作者： Wang, Zhen Liu, Lizhi Hubei Key Laboratory of Intelligent Robot School of Computer Science and Engineering Artificial Intelligence Wuhan Institute of Technology Wuhan430205 China

ISBN: (纸本)9798400716966

PM2.5 concentration is one of the important indicators for measuring air quality. In order to enhance the precision of PM2.5 concentration forecasting, a short-Term prediction model for PM2.5 concentration based on SA-LSTM (Self Attention Long Short Term Memory) is proposed. LSTM stores and transmits the update information of the previous time step through cell state and calculates the output vectors of each time step in the temporal input. Self Attention extracts the internal dependency relationships between multiple output vectors and weights them to obtain a key output vector that integrates global input information. The experiment selected air quality monitoring data from the Yangshoujing Avenue Automatic Air Quality Monitoring Station in Yidu City, Yichang City from January 1, 2019 to December 31, 2020. The results showed that using the SA-LSTM model to predict the PM2.5 concentration in the next hour reduced RMSE and MAE by 18% and 11% respectively, and increased R2 by 3.78% compared to the benchmark LSTM model. © 2023 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction

arXiv

引用

arXiv 2024年

作者： Curtis, Aidan Kumar, Nishanth Cao, Jing Lozano-Pérez, Tomás Kaelbling, Leslie Pack MIT Computer Science and Artificial Intelligence Laboratory United States

Recent developments in pretrained large language models (LLMs) applied to robotics have demonstrated their capacity for sequencing a set of discrete skills to achieve open-ended goals in simple robotic tasks. In this paper, we examine the topic of LLM planning for a set of continuously parameterized skills whose execution must avoid violations of a set of kinematic, geometric, and physical constraints. We prompt the LLM to output code for a function with open parameters, which, together with environmental constraints, can be viewed as a Continuous Constraint Satisfaction Problem (CCSP). This CCSP can be solved through sampling or optimization to find a skill sequence and continuous parameter settings that achieve the goal while avoiding constraint violations. Additionally, we consider cases where the LLM proposes unsatisfiable CCSPs, such as those that are kinematically infeasible, dynamically unstable, or lead to collisions, and re-prompt the LLM to form a new CCSP accordingly. Experiments across simulated and real-world domains demonstrate that our proposed strategy, PRoC3S, is capable of solving a wide range of complex manipulation tasks with realistic constraints much more efficiently and effectively than existing baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Learning to Look Around: Enhancing Teleoperation and Learning with a Human-like Actuated Neck

arXiv

引用

arXiv 2024年

作者： Sen, Bipasha Wang, Michelle Thakur, Nandini Agarwal, Aditya Agrawal, Pulkit MIT Computer Science and Artificial Intelligence Laboratory United States

We introduce a teleoperation system that integrates a 5-DOF actuated neck, designed to replicate natural human head movements and perception. By enabling behaviors like "peeking" or "tilting", the system provides operators with a more intuitive and comprehensive view of the environment, improving task performance, reducing cognitive load, and facilitating complex whole-body manipulation. We demonstrate the benefits of natural perception across seven challenging teleoperation tasks, showing how the actuated neck enhances the scope and efficiency of remote operation. Furthermore, we investigate its role in training autonomous policies through imitation learning. In three distinct tasks, the actuated neck supports better spatial awareness, reduces distribution shift, and enables adaptive task-specific adjustments compared to a static wide-angle camera. Copyright © 2024, The Authors. All rights reserved.

关键词： Remote control

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：