检索结果-内蒙古大学图书馆

IEEE Transactions on artificial intelligence 2025年第6期6卷 1488-1501页

作者： Saday, Artun Demirel, Ilker Yildirim, Yigit Tekin, Cem Bilkent University Department of Electrical and Electronics Engineering Ankara06800 Turkey Massachusetts Institute of Technology Computer Science & Artificial Intelligence Laboratory CambridgeMA02139 United States

Multiarmed bandits (MAB) is a sequential decision-making model in which the learner controls the trade-off between exploration and exploitation to maximize its cumulative reward. Federated multiarmed bandits (FMAB) is an emerging framework where a cohort of learners with heterogeneous local models play an MAB game and communicate their aggregated feedback to a server to learn a globally optimal arm. Two key hurdles in FMAB are communication-efficient learning and resilience to adversarial attacks. To address these issues, we study the FMAB problem in the presence of Byzantine clients who can send false model updates threatening the learning process. We analyze the sample complexity and the regret of β-optimal arm identification. We borrow tools from robust statistics and propose a median-of-means (MoM)-based online algorithm, Fed-MoM-UCB, to cope with Byzantine clients. In particular, we show that if the Byzantine clients constitute less than half of the cohort, the cumulative regret with respect to \beta-optimal arms is bounded over time with high probability, showcasing both communication efficiency and Byzantine resilience. We analyze the interplay between the algorithm parameters, a discernibility margin, regret, communication cost, and the arms’ suboptimality gaps. We demonstrate Fed-MoM-UCB's effectiveness against the baselines in the presence of Byzantine attacks via experiments. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Learning Intensity and Optical Flow from High-speed Spike Stream

引用

IEEE Transactions on Circuits and Systems for Video Technology 2024年第6期35卷 5126-5139页

作者： Zhu, Lin Yan, Weiquan Chang, Yi Tian, Yonghong Huang, Hua Beijing Institute of Technology School of Computer Science and Technology Beijing100081 China Peng Cheng Laboratory Shenzhen518055 China Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Peking University School of Computer Science Beijing100081 China Beijing Normal University School of Artificial Intelligence Beijing100875 China

Bio-inspired vision sensors, which emulate the human retina by recording light intensity as binary spikes, have gained increasing interest in recent years. Among them, the spike camera is capable of perceiving fine textures by simulating a small retinal region called the fovea and producing high temporal resolution (20,000 Hz) spatiotemporal spike streams. To bridge the gap between binary spike streams and human vision in high-speed scenes, reconstructing intensity and optical flow from high temporal resolution spikes is particularly important. In this paper, we present a hybrid SNN-ANN network designed for simultaneous intensity and optical flow learning from spike streams. To adaptively extract spatial and temporal features from continuous spike streams, we propose a spiking neuron module with dense connections that efficiently processes both short-term and long-term spike data, while maintaining low power consumption characteristics. Subsequently, we introduce two decoders for optical flow and intensity estimation that complement each other. A temporal-aware warping module, based on flow features, is specifically designed to align the temporal features of the intensity decoder, thereby reducing motion artifacts. Concurrently, improved intensity features contribute to more accurate flow feature predictions, resulting in a mutually beneficial relationship within our network. To evaluate the effectiveness of our proposed network, we conduct experiments on both simulated and real spike datasets. Our network outperforms existing state-of-the-art spike-based reconstruction and optical flow estimation methods, demonstrating its potential for advancing the field of bio-inspired vision sensors. Our code is available at https://***/LinZhu111/SLIO. © 1991-2012 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

End-to-end learning of 3D phase-only holograms for holographic display

引用

Light(science & Applications) 2022年第9期11卷 2176-2193页

作者： Liang Shi Beichen Li Wojciech Matusik Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology32 Vassar StCambridgeMA 02139USA

computer-generated holography(CGH)provides volumetric control of coherent wavefront and is fundamental to applications such as volumetric 3D displays,lithography,neural photostimulation,and optical/acoustic ***,deep learning-based methods emerged as promising computational paradigms for CGH synthesis that overcome the quality-runtime tradeoff in conventional simulation/optimization-based ***,the quality of the predicted hologram is intrinsically bounded by the dataset's *** we introduce a new hologram dataset,MIT-CGH-4K-V2,that uses a layered depth image as a data-efficient volumetric 3D input and a two-stage supervised+unsupervised training protocol for direct synthesis of high-quality 3D phase-only *** proposed system also corrects vision aberration,allowing customization for *** experimentally show photorealistic 3D holographic projections and discuss relevant spatial light modulator calibration *** method runs in real-time on a consumer GPU and 5 FPS on an iPhone 13 Pro,promising drastically enhanced performance for the applications above.

关键词： holographic synthesis overcome

来源：评论

学校读者我要写书评

暂无评论

Software Engineering Research in a World with Generative artificial intelligence 24

Software Engineering Research in a World with Generative Art...

引用

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Rinard, Martin Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science CambridgeMA United States

Generative artificial intelligence systems such as large language models (LLMs) exhibit powerful capabilities that many see as the kind of flexible and adaptive intelligence that previously only humans could exhibit. ... 详细信息

ISBN: (纸本)9798400702174

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

引用

Chinese Journal of Electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

来源：评论

学校读者我要写书评

暂无评论

Graph Augmentation Empowered Contrastive Learning for Recommendation

引用

ACM Transactions on Information Systems 2025年第2期43卷 1-27页

作者： Xu, Lixiang Liu, Yusheng Xu, Tong Chen, Enhong Tang, Yuanyan School of Artificial Intelligence and Big Data Hefei University Hefei China State Key Laboratory of Cognitive Intelligence School of Computer Science and Technology University of Science and Technology of China Hefei China Zhuhai UM Science and Technology Research Institute FST University of Macau China

The application of contrastive learning (CL) to collaborative filtering (CF) in recommender systems has achieved remarkable success. CL-based recommendation models mainly focus on creating multiple augmented views by employing different graph augmentation methods and utilizing these views for self-supervised learning. However, current CL methods for recommender systems usually struggle to fully address the problem of noisy data. To address this problem, we propose the Graph Augmentation Empowered Contrastive Learning (GAECL) for recommendation framework, which uses graph augmentation based on topological and semantic dual adaptation and global co-modeling via structural optimization to co-create contrasting views for better augmentation of the CF paradigm. Specifically, we strictly filter out unimportant topologies by reconstructing the adjacency matrix and mask unimportant attributes in nodes according to the PageRank centrality principle to generate an augmented view that filters out noisy data. Additionally, GAECL achieves global collaborative modeling through structural optimization and generates another augmented view based on the PageRank centrality principle. This helps to filter the noisy data while preserving the original semantics of the data for more effective data augmentation. Extensive experiments are conducted on five datasets to demonstrate the superior performance of our model over various recommendation models. © 2025 Copyright held by the owner/author(s).

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Variational Inference-Based LSTM-enhanced Deep Neural Model for Sequential Recommendations

引用

IEEE Access 2025年 13卷 95945-95962页

作者： Ngaffo, Armielle Noulapeu Kamgang, Ines Raissa Djouela Maka, Ebenezer Maka Malong, Yannick University of Douala Laboratory of Computer Science Data Science and Artificial Intelligence National Higher Polytechnic School of Douala Douala8580 Cameroon Department of computer engineering University of Buea Faculty of Engineering and Technology Cameroon

Long Short-Term Memory (LSTM) networks are particularly useful in recommender systems since user preferences change over time. Unlike traditional recommender models which assume static user-item interactions, LSTM models capture sequential dependencies and temporal dynamics, making them ideal for personalized, session-based, and sequential recommendation tasks. However, traditional LSTM-based recommender systems do not model uncertainty since they perform deterministic predictions. Moreover, those recommender models exhibit poor generalization on small datasets, and poor-handle cold-start and data sparsity problems. To overcome those limitations, this paper presents an LSTM-based recommender model that leverages an improved deep matrix factorization to accurately address the data sparsity problem. In addition, an enhanced variational inference coupled to the Evidence Lower Bound Optimization is applied on LSTM unit layers to perform uncertainty-aware predictions. Thereafter, latent vectors obtained from LSTM networks are effectively involved in the sequential recommendation process. Experiments have been conducted on several real-world datasets to evaluate our proposal and the results show the proposed model presents significant performances compared to state-of-the-art models. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

LGNet: Linear Graph Representation for Efficient Cold-Start Recommendations

LGNet: Linear Graph Representation for Efficient Cold-Start ...

引用

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

作者： Li, Zhenglong Luo, Ruiqi Wang, Bangchao Li, Lin Zhong, Xian School of Computer Science and Artificial Intelligence Wuhan Textile University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798350368741

Graph Convolutional Networks (GCNs) demonstrate significant potential in recommendation systems but face difficulties with the cold-start problem, especially in integrating new nodes during inference. The typical solution leverages meta-learning for few-shot learning, though it often fails to fully capture collaborative filtering between nodes. In this paper, we revisit the node embedding propagation algorithm in GCNs, emphasizing the importance of collaborative filtering and elucidating the relation between high-order and low-order embeddings. Given the substantial interaction data required for training recommendation models, maintaining a simple model structure remains crucial. To address these challenges, we propose the Linear Graph Network (LGNet), which theoretically compresses multi-layer GCNs into a single layer, enabling the embedding of new nodes during inference. Experimental results on benchmark datasets for link prediction and user cold-start tasks demonstrate that LGNet outperforms existing methods. The code will be available at https://***/kunbeibei/LGNet. © 2025 IEEE.

关键词： Cold-Start Problem Graph Convolutional Networks Linear Representation Recommendation Systems

来源：评论

学校读者我要写书评

暂无评论

Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models without Preference Data

Inverse-Q*: Token Level Reinforcement Learning for Aligning ...

引用

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

作者： Xia, Han Gao, Songyang Ge, Qiming Xi, Zhiheng Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University Shanghai China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (纸本)9798891761681

Reinforcement Learning from Human Feedback (RLHF) has proven effective in aligning large language models with human intentions, yet it often relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and present challenges in sample efficiency and *** this paper, we introduce Inverse-Q*, an innovative framework that transcends traditional RL methods by optimizing token-level reinforcement learning without the need for additional reward or value ***-Q* leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model's responses, facilitating more granular and flexible policy *** approach reduces reliance on human annotation and external supervision, making it especially suitable for low-resource *** present extensive experimental results demonstrating that Inverse-Q* not only matches but potentially exceeds the effectiveness of PPO in terms of convergence speed and the alignment of model responses with human *** findings suggest that Inverse-Q* offers a practical and robust alternative to conventional RLHF approaches, paving the way for more efficient and adaptable model training approaches. © 2024 Association for Computational Linguistics.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Advancements in Cardiotoxicity Detection and Assessment through artificial intelligence: A Comprehensive Review 4

Advancements in Cardiotoxicity Detection and Assessment thro...

引用

4th International Conference on Innovative Research in Applied science, Engineering and Technology, IRASET 2024

作者： Bouatmane, Ahmed Daaif, Abdelaziz Bousselham, Abdelmajid Higher Normal School Of Technical Education Computer Science Artificial Intelligence And Cybersecurity Laboratory Mohammadia Morocco

ISBN: (数字)9798350309508

ISBN: (纸本)9798350309508

This comprehensive review critically examines the forefront of artificial intelligence (AI) applications in cardiology, focusing on detecting and assessing cardiotoxicity and heart failure. It discusses various studies that demonstrate AI's revolutionary impact on cardiac healthcare, including deep learning for predicting pharmaceutical cardiotoxic effects, advanced AI models for identifying cardiotoxicity in stem cell-derived cardiomyocytes, and AI-enhanced imaging for monitoring cardiac complications in cancer patients. The review also explores AI systems for detecting early signs of heart failure in electrocardiograms and computational models for predicting drug interactions with hERG channels, which are vital for cardiac safety assessments. Additionally, it highlights the use of AI in preclinical research and drug safety evaluations. The reviewed studies underscore the potential of AI, especially deep learning techniques, in predicting and detecting drug-induced cardiotoxicity, offering new perspectives in assessing cardiotoxicity risks prior to drug administration and detecting early cardiac damage. However, the paper notes the necessity for further studies to validate and refine these AI models and suggests the integration of more diverse data and considerations for improved predictive performance. © 2024 IEEE.

关键词： Risk assessment

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：