检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Christopher Wang Adam Yaari Aaditya K. Singh Vighnesh Subramaniam Dana Rosenfarb Jan DeWitt Pranav Misra Joseph R Madsen Scellig Stone Gabriel Kreiman Boris Katz Ignacio Cases Andrei Barbu Computer Science and Artificial Intelligence Laboratory MIT and Center for Brains Minds and Machines MIT Computer Science and Artificial Intelligence Laboratory MIT and Gatsby Computational Neuroscience Unit University College London Computer Science and Artificial Intelligence Laboratory MIT Center for Brains Minds and Machines MIT and Center for Brain Science Harvard University and Boston Children's Hospital Harvard Medical School Boston Children's Hospital Harvard Medical School

ISBN: (纸本)9798331314385

We present the Brain Treebank, a large-scale dataset of electrophysiological neural responses' recorded from intracranial probes while 10 subjects watched one or more Hollywood movies. Subjects watched on average 2.6 Hollywood movies, for an average viewing time of 4.3 hours, and a total of 43 hours. The audio track for each movie was transcribed with manual corrections. Word onsets were manually annotated on spectrograms of the audio track for each movie. Each transcript was automatically parsed and manually corrected into the universal dependencies (UD) formalism' assigning a part of speech to every word and a dependency parse to every sentence. In total, subjects heard over 38,000 sentences (223,000 words), while they had on average 168 electrodes implanted. This is the largest dataset of intracranial recordings featuring grounded naturalistic language, one of the largest English UD treebanks in general' and one of only a few UD treebanks aligned to multimodal features. We hope that this dataset serves as a bridge between linguistic concepts' perception' and their neural representations. To that end, we present an analysis of which electrodes are sensitive to language features while also mapping out a rough time course of language processing across these electrodes. The Brain Treebank is available at https://***/

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Personalized Imputations for Patient Health Status Prediction in Electronic Health Records

Generating Personalized Imputations for Patient Health Statu...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Yang Zhang, Weiyu Si, Jiasheng Li, Zhao Peng, Xueping Lu, Wenpeng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Evay Info Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China University of Technology Sydney Australian Artificial Intelligence Institute Sydney Australia

ISBN: (纸本)9798350386226

Electronic health records (EHRs) play a crucial role in the development of personalized treatment plans for patients. However, EHRs are often highly incomplete, posing significant challenges for predictive modeling. While existing deep learning models employ various imputation techniques to reconstruct missing values, they often fail to represent missing data in a personalized manner and do not learn from the missingness patterns in EHRs data. This limitation reduces their effectiveness in practical personalized healthcare applications. To address this issue, we propose SPIME, a self-supervised model that generates personalized imputations in EHRs data for patient health status prediction. We introduce a personalized missing mask (PMM) based on the frequency of feature measurements. Additionally, we incorporate a masked imputation task (MIT) loss that minimizes the loss of artificially introduced missing values, thereby enhancing the model's capability to handle missing data. SPIME adopts self-supervised pretraining to learn representations from personalized missing patterns and reconstructs missing data in the latent space. To further enhance representation learning, two independent attention mechanisms are applied separately across the feature and temporal dimensions. Experimental results on two real-world EHRs datasets show that SPIME outperforms existing state-of-the-art methods in predicting in-hospital mortality and decompensation, demonstrating its effectiveness in reconstructing missing data and predicting patient health status. The code will be published at https://***/cling6666/SPIME. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Automatic Difficulty Balance in Two-Player Games with Deep Reinforcement Learning

Automatic Difficulty Balance in Two-Player Games with Deep R...

引用

IEEE Symposium on Computational intelligence and Games, CIG

作者： Simão Reis Rita Novais Luís Paulo Reis Nuno Lau Artificial Intelligence and Computer Science Laboratory (LIACC) Faculty of Engineering University of Porto Porto Portugal Institute of Electronics and Informatics Engineering of Aveiro (IEETA) University of Aveiro Aveiro Portugal

Regardless of the goal of a game, it should be a pleasant and fun experience for its players. For some games to be enjoyable, the level of difficulty must be carefully calibrated, otherwise, players will feel bored or frustrated. Multiplayer scenarios in particular, where one player’s satisfaction might not translate to the enjoyment of other players and poses extra challenges in balancing the difficulty. The performance of one player is relative to the opponent, versus single-player scenarios where we can fully control the environment. We propose an AI automation framework for difficulty balancing in two-player games, where balancing is seen as a Reinforcement Learning task. A Game Master (GM) agent learns how to use handicap game mechanics, signaled by a reward function that evaluates a weighted combination of aesthetic criteria that encourages dramatization and allows a player in the lead to go back and a player in the rear to catch up, creating the desired rubber banding effect that balances out skill gaps. The quality of the games with the trained GM embedded is examined by measuring the same aesthetic criteria on the resulting games, and by analyzing the resulting changes in the game.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Network Security Evaluation for Space-Ground Integrated Networks Based on Network Simulation 8

Network Security Evaluation for Space-Ground Integrated Netw...

引用

8th International Conference on Data science in Cyberspace, DSC 2023

作者： Ye, Haibo Zhao, Lei Tao, Leiting Wang, Xiaofeng The 6th Research Institute of China Electronics Corporation Beijing China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9798350331035

Space-ground integrated networks (SGINs) have become an important direction of future network development. However, SGINs face many security threats because of the multidimensional heterogeneity of their structure. Therefore, effective network security evaluation is an indispensable part of SGIN security research. Most existing network security evaluations are oriented toward network environments with simple structures and small scales and cannot be applied to SGINs. This paper reports the simulation of realistic SGIN scenarios through network simulation. Based on such network simulation, this paper proposes a network security evaluation suitable for SGINs that realizes the evaluation of the security risks and threats to SGINs in order to further improve their security. First, a SGIN security evaluation architecture is constructed to hierarchically describe the SGIN security evaluation process. Then, considering the characteristics of SGINs and abnormal network behavior characteristics, a SGIN security evaluation index system is designed, laying a foundation for the security evaluation of SGINs. Second, in view of the requirements of security evaluation data collection, a data collection method with multiple categories of indices is proposed, which not only guarantees the effectiveness of data collection but also improves the collection efficiency. Finally, based on game theory, a network security evaluation model is designed for the systematic security evaluation requirements of SGINs. This model realizes the effective evaluation of the effects of abnormal network behavior while accounting for subjective intentions and objective patterns. Experimental results show that the proposed technique can effectively gather information about system data resources through data collection. At the same time, the proposed network security evaluation model conforms to the patterns of abnormal network behavior and effectively meets the needs of security evaluation for SGINs. © 202

关键词： data collection network security evaluation network simulation space-ground integrated network

来源：评论

学校读者我要写书评

暂无评论

Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction 30

Take Care of Your Prompt Bias! Investigating and Mitigating ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Xu, Ziyang Peng, Keqin Ding, Liang Tao, Dacheng Lu, Xiliang Institute of Artificial Intelligence School of Computer Science Wuhan University China School of Mathematics and Statistics Wuhan University China Hubei Key Laboratory of Computational Science Wuhan University China Beihang University China The University of Sydney Australia Nanyang Technological University Singapore

ISBN: (纸本)9782493814104

Recent research shows that pre-trained language models (PLMs) suffer from "prompt bias" in factual knowledge extraction, i.e., prompts tend to introduce biases toward specific labels. Prompt bias presents a significant challenge in assessing the factual knowledge within PLMs. Therefore, this paper aims to improve the reliability of existing benchmarks by thoroughly investigating and mitigating prompt bias. We show that: 1) all prompts in the experiments exhibit non-negligible bias, with gradient-based prompts like AutoPrompt and OptiPrompt displaying significantly higher levels of bias;2) prompt bias can amplify benchmark accuracy unreasonably by overfitting the test datasets, especially on imbalanced datasets like LAMA. Based on these findings, we propose a representation-based approach to mitigate the prompt bias during inference time. Specifically, we first estimate the biased representation using prompt-only querying, and then remove it from the model's internal representations to generate the debiased representations, which are used to produce the final debiased outputs. Experiments across various prompts, PLMs, and benchmarks show that our approach can not only correct the overfitted performance caused by prompt bias, but also significantly improve the prompt retrieval capability (up to 10% absolute performance gain). These results indicate that our approach effectively alleviates prompt bias in knowledge evaluation, thereby enhancing the reliability of benchmark assessments. Hopefully, our plug-and-play approach can be a golden standard to strengthen PLMs toward reliable knowledge bases. Code and data are released in https://***/FelliYang/PromptBias. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Semantic Data Augmentation for Few-Shot Biomedical Named Entity Recognition

Semantic Data Augmentation for Few-Shot Biomedical Named Ent...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Ying Wang, Weihua 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)9798350368741

Biomedical Named Entity Recognition (BioNER) aims to identify and classify entities in biomedical text. This task struggles with data scarcity due to limited annotated data. Although data augmentation is effective, existing methods fail to handle the complex semantic mappings on biomedical terminology, which results in the generated samples lacking semantic diversity. In this paper, we propose a data augmentation method to create semantically diverse and coherent training samples for few-shot BioNER. The method utilizes the Unified Medical Language System (UMLS) for entity replacement and combines with a Masked Language Model (MLM) to generate contextually relevant words. Experimental results show that our method improves BioNER performance in few-shot scenarios. Compared to all baseline models, our method achieves an average F1 score improvement of 7.6% and 11.6% on the NCBI and JNLPBA datasets, respectively. Our source code and data are available at https://***/ABC8184/SDA. © 2025 IEEE.

关键词： BioNER data augmentation few-shot learning masked language model UMLS

来源：评论

学校读者我要写书评

暂无评论

Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation 31

Distance-Adaptive Quaternion Knowledge Graph Embedding with ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Weihua Liang, Qiuyu 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)9798891761964

Quaternion contains one real part and three imaginary parts, which provided a more expressive hypercomplex space for learning knowledge graph. Existing quaternion embedding models measure the plausibility of a triplet through either semantic matching or geometric distance scoring functions. However, it appears that semantic matching diminishes the separability of entities, while the distance scoring function weakens the semantics of entities. To address this issue, we propose a novel quaternion knowledge graph embedding model. Our model combines semantic matching with the geometric distance of entities to better measure the plausibility of triplets. Specifically, in the quaternion space, we perform a right rotation on head entity and a reverse rotation on tail entity to learn rich semantic features. We then utilize distance-adaptive translations to learn geometric distance between entities. Furthermore, we provide mathematical proofs to demonstrate our model can handle complex logical relationships. Extensive experimental results and analyses show our model significantly outperforms previous models on well-known knowledge graph completion benchmark datasets. Our code is available at https://***/llqy123/DaBR. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation Modeling

arXiv

引用

arXiv 2024年

作者： Zhao, Yueming Yuan, Xuening Yang, Hongyu Huang, Di School of Computer Science and Engineering Beihang University Beijing China School of Artificial Intelligence Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

Recent advances in text-to-3D creation integrate the potent prior of Diffusion Models from text-to-image generation into 3D domain. Nevertheless, generating 3D scenes with multiple objects remains challenging. Therefore, we present DreamScape, a method for generating 3D scenes from text. Utilizing Gaussian Splatting for 3D representation, DreamScape introduces 3D Gaussian Guide that encodes semantic primitives, spatial transformations and relationships from text using LLMs, enabling local-to-global optimization. Progressive scale control is tailored during local object generation, addressing training instability issue arising from simple blending in the global optimization stage. Collision relationships between objects are modeled at the global level to mitigate biases in LLMs priors, ensuring physical correctness. Additionally, to generate pervasive objects like rain and snow distributed extensively across the scene, we design specialized sparse initialization and densification strategy. Experiments demonstrate that DreamScape achieves state-of-the-art performance, enabling high-fidelity, controllable 3D scene generation. Copyright © 2024, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Adversarial Example Transferability via Regularized Constrained Feature Layer

引用

computers, Materials & Continua 2025年第4期83卷 157-175页

作者： Xiaoyin Yi Long Chen Jiacheng Huang Ning Yu Qian Huang School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Chongqing Key Laboratory of Public Big Data Security Technology Chongqing401420China School of Cyber Security and Information Law Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of EducationChongqing400065China Artificial Intelligence and Big Data College Chongqing Polytechnic University of Electronic TechnologyChongqing401331China

Transfer-based Adversarial Attacks(TAAs)can deceive a victim model even without prior *** is achieved by leveraging the property of adversarial *** is,when generated from a surrogate model,they retain their features if applied to other models due to their good ***,adversarial examples often exhibit overfitting,as they are tailored to exploit the particular architecture and feature representation of source ***,when attempting black-box transfer attacks on different target models,their effectiveness is *** solve this problem,this study proposes an approach based on a Regularized Constrained Feature Layer(RCFL).The proposed method first uses regularization constraints to attenuate the initial examples of low-frequency *** are then added to a pre-specified layer of the source model using the back-propagation technique,in order to modify the original adversarial ***,a regularized loss function is used to enhance the black-box transferability between different target *** proposed method is finally tested on the ImageNet,CIFAR-100,and Stanford Car datasets with various target models,The obtained results demonstrate that it achieves a significantly higher transfer-based adversarial attack success rate compared with baseline techniques.

关键词： Adversarial examples black-box transferability regularized constrained transfer-based adversarial attacks

来源：评论

学校读者我要写书评

暂无评论

Progressive Self-supervised Representation Learning for 3D Facial Expression Recognition

Progressive Self-supervised Representation Learning for 3D F...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Hebeizi Li Hongyu Yang Di Huang School of Computer Science and Engineering Beihang University Beijing China Institute of Artificial Intelligence Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (数字)9798350364132

ISBN: (纸本)9798350364149

Facial expression recognition (FER) is a critical area of research in face analysis. While 2D data has been extensively used, 3D data offers inherent advantages, such as increased resilience to illumination and pose variations. However, the limited size of current 3D FER datasets significantly constrains the performance of 3D FER methods. To overcome this challenge, we propose a novel self-supervised pre-training scheme by leveraging large-scale external 3D data, followed by fine-tuning on 3D FER datasets. Our approach starts with self-supervised learning on a large-scale 3D point cloud object dataset, specifically ShapeNet. We then move on to the FaceScape dataset, which is primarily used for morphable face prediction. To enhance robustness, we integrate synthetic data before fine-tuning on specific FER datasets. This multi-stage process allows the model to progressively learn 3D facial expression representations from coarse to fine. For this purpose, we utilize Point-MAE, a leading self-supervised model for representation learning. To enhance its ability for FER task, we further incorporate facial priors in the masking and point sampling steps, leveraging the distinctive characteristics of facial data. Our method achieves state-of-the-art performance on both BU-3DFE and Bosphorus datasets, matching or surpassing results achieved by other 2D+3D FER techniques.

关键词： Representation learning Training Point cloud compression Solid modeling Three-dimensional displays Face recognition Self-supervised learning Robustness Synthetic data Resilience

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：