检索结果-内蒙古大学图书馆

International Conference on Computing and Networking Technology (ICCNT)

作者： Ankita Agarwal Nagaraj Patil M. Rajeswari Gitanjali B. Yadav Rahul Mishra Gourav Sood Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Mechanical Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Ramnagar District Karnataka India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Technology Pune INDIA Department of Electrical Engineering Vivekananda Global University Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Deep gaining knowledge of and records science are the most important and surprisingly influential fields of technology. Deep studying can system extensive statistics to discover styles, create insights, and have their personal choices concerning further analysis. Facts and technological know-how are centered on information-pushed business selection-making, using predictive analytics, machine studying, and other more recent algorithms to perceive, refine, and increase intelligent choices based on information. Those fields are rapidly developing and overlapping, creating an ever-increasing demand for each technical professionals and people with an intensive knowledge of statistics science and deep mastering. Integrating deep gaining knowledge of and records technology can create some challenges and possibilities which have to be explored.

关键词： Deep learning Portable computers Accuracy data science Prediction algorithms Complexity theory data mining Predictive analytics Business

来源：评论

学校读者我要写书评

暂无评论

Cross Architecture Distillation for Face Recognition

arXiv

引用

arXiv 2023年

作者： Zhao, Weisong Zhu, Xiangyu He, Zhixiang Zhang, Xiao-Yu Lei, Zhen Institute of Information Engineering Chinese Academy of Sciences Beijing China CBSR&NLPR Institute of Automation Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China China Telecom Corporation Ltd. Data & AI Technology Company China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong

Transformers have emerged as the superior choice for face recognition tasks, but their insufficient platform acceleration hinders their application on mobile devices. In contrast, Convolutional Neural Networks (CNNs) capitalize on hardware-compatible acceleration libraries. Consequently, it has become indispensable to preserve the distillation efficacy when transferring knowledge from a Transformer-based teacher model to a CNN-based student model, known as Cross-Architecture Knowledge Distillation (CAKD). Despite its potential, the deployment of CAKD in face recognition encounters two challenges: 1) the teacher and student share disparate spatial information for each pixel, obstructing the alignment of feature space, and 2) the teacher network is not trained in the role of a teacher, lacking proficiency in handling distillation-specific knowledge. To surmount these two constraints, 1) we first introduce a Unified Receptive Fields Mapping module (URFM) that maps pixel features of the teacher and student into local features with unified receptive fields, thereby synchronizing the pixel-wise spatial information of teacher and student. Subsequently, 2) we develop an Adaptable Prompting Teacher network (APT) that integrates prompts into the teacher, enabling it to manage distillation-specific knowledge while preserving the model’s discriminative capacity. Extensive experiments on popular face benchmarks and two large-scale verification sets demonstrate the superiority of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation 21

Diversity-Promoting Deep Reinforcement Learning for Interact...

引用

5th International Conference on Crowd science and engineering

作者： Yong Liu Zhiqi Shen Yinan Zhang Lizhen Cui Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY) Nanyang Technological University Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR) & School of Software Shandong University China

ISBN: (纸本)9781450395540

The interactive recommendation systems have recently attracted lots of research attentions, because they can model the interactions between the user and the recommender system. Most previous interactive recommendation methods only focus on optimizing recommendation accuracy. However, they usually overlook other important aspects of recommendation quality, e.g., the diversity of recommendation results. In this work, we propose a novel recommendation framework, called Diversity-promoting Deep Reinforcement Learning (D2RL), which aims to promote the diversity of interactive recommendation results. In D2RL, the Determinantal Point Process (DPP) is used to generate diverse, while relevant item recommendations. For each user, a personalized DPP kernel matrix is maintained, which is constructed from two parts: a fixed similarity matrix capturing item-item similarity, and the relevance of items dynamically learnt through an actor-critic reinforcement learning framework. To demonstrate the effectiveness of the proposed D2RL model, we have performed extensive offline experiments as well as simulated online experiments with real-world datasets.

关键词： Determinantal Point Process Diversity Reinforcement Learning Interactive Recommendation

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Network Security through AIDriven Intrusion Detection with Hybrid AutoencoderGAN Fusion 23

Enhancing IoT Network Security through AIDriven Intrusion De...

引用

Proceedings of the 5th International Conference on Information Management & Machine intelligence

作者： Rupali A. Mahajan Sukhvinder Singh Dari Ritika Dhabliya Gabriela Michael Anil Kumar Nidhi Ranjan Computer Associate Professor COMP VIIT Pune Maharashtra India Computer Associate Professor Symbiosis Law School Nagpur Campus Symbiosis International (Deemed University) Pun India Computer Director Yashika Journal Publications Pvt. Limited Wardha Maharashtra India India Computer Symbiosis Law School Nagpur Campus Symbiosis International (Deemed University) Pune India India Department of Artificial Intelligence & Data Science Professor Poornima Institute Of Engineering &Technology Jaipur Rajasthan India India Computer Associate Professor Vasantdada Patil Pratishthan?s College of engineering and Visual Arts Mumbai Maharashtra India India

ISBN: (纸本)9798400709418

The rapid growth of Internet of Things (IoT)IoT devices has changed how we connect and interact with our environment. This advancement has also complicated network security. As IoT networks grow, data integrity and confidentiality become more important. This study integrates a hybrid autoencoder and Generative Adversarial Network (GAN) model to use AI to solve security problems. The UNSW-NB15 dataset, a benchmark for network IDSs, is used to rigorously evaluate the proposed model. An autoencoder and GAN combination offers promising IDS for IoT networks. The autoencoder component excels at capturing concise and illustrative data representations, enabling it to spot network anomalies. The GAN component improves the model's ability to generate synthetic data samples that closely resemble network traffic patterns, making it easier to identify complex and novel attacks. The UNSW-NB15 dataset is known for its extensive network traffic data, making it ideal for testing the proposed artificial intelligence-based IDS. The proposed hybrid model achieves 99.13% accuracy. The result outperforms traditional DL methods. The proposed model's increased precision shows its ability to detect and address network anomaly risks. The proposed system is evaluated using precision, recall, F1-Score, AUC-ROC, MCC, and Cohen's Kappa. The thorough evaluation shows that the Proposed hybrid autoencoder-GAN model provides a complete and efficient IoT network security solution in all dimensions. In conclusion, artificial intelligence-based intrusion detection and a hybrid model that combines autoencoder and generative adversarial network techniques improve IoT network security. The model's UNSW-NB15 dataset accuracy shows its ability to protect IoT ecosystems from many threats. This study helps improve the reliability and robustness of networks, boosting confidence in the growing world of interconnected devices.

关键词： Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks

arXiv

引用

arXiv 2025年

作者： Khot, Ayush Wang, Xiwei Roy, Avik Kindratenko, Volodymyr Neubauer, Mark S. Department of Physics University of Illinois Urbana-Champaign UrbanaIL61801 United States The Grainger College of Engineering Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign UrbanaIL61801 United States Center for Artificial Intelligence Innovation National Center for Supercomputing Applications University of Illinois Urbana-Champaign UrbanaIL61801 United States The Grainger College of Engineering Siebel School of Computing and Data Science University of Illinois Urbana-Champaign UrbanaIL61801 United States

Current methods commonly used for uncertainty quantification (UQ) in deep learning (DL) models utilize Bayesian methods which are computationally expensive and time-consuming. In this paper, we provide a detailed study of UQ based on evidential deep learning (EDL) for deep neural network models designed to identify jets in high energy proton-proton collisions at the Large Hadron Collider and explore its utility in anomaly detection. EDL is a DL approach that treats learning as an evidence acquisition process designed to provide confidence (or epistemic uncertainty) about test data. Using publicly available datasets for jet classification benchmarking, we explore hyperparameter optimizations for EDL applied to the challenge of UQ for jet identification. We also investigate how the uncertainty is distributed for each jet class, how this method can be implemented for the detection of anomalies, how the uncertainty compares with Bayesian ensemble methods, and how the uncertainty maps onto latent spaces for the models. Our studies uncover some pitfalls of EDL applied to anomaly detection and a more effective way to quantify uncertainty from EDL as compared with the foundational EDL setup. These studies illustrate a methodological approach to interpreting EDL in jet classification models, providing new insights on how EDL quantifies uncertainty and detects out-of-distribution data which may lead to improved EDL methods for DL models applied to classification tasks. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Agile Meets Quantum: A Novel Genetic Algorithm Model for Predicting the Success of Quantum Software Development Project

arXiv

引用

arXiv 2024年

作者： Khan, Arif Ali Akbar, Muhammad Azeem Lahtinen, Valtteri Paavola, Marko Niazi, Mahmood Alatawi, Mohammed Naif Alotaibi, Shoayee Dlaim M3S Empirical Software Engineering Research Unit University of Oulu Oulu90014 Finland Software Engineering Department Lappeenranta-Lahti University of Technology Lappeenranta53851 Finland Quanscient Oy Tampere Finland VTT Technical Research Ctr of Finland Ltd Oulu Finland Department of Information and Computer Science King Fahd University of Petroleum and Minerals Saudi Arabia Interdisciplinary Research Centre for Intelligent Secure Systems King Fahd University of Petroleum and Minerals Saudi Arabia Information Technology Department Faculty of Computers and Information Technology University of Tabuk Saudi Arabia Department of Artificial Intelligence and Data Science College of Computer Science and Engineering University of Hail Hail Saudi Arabia

Context: Quantum software systems represent a new realm in software engineering, utilizing quantum bits (Qubits) and quantum gates (Qgates) to solve the complex problems more efficiently than classical counterparts. Agile software development approaches are considered to address many inherent challenges in quantum software development, but their effective integration remains unexplored. Objective: This study investigates key causes of challenges that could hinders the adoption of traditional agile approaches in quantum software projects and develop an Agile-Quantum Software Project Success Prediction Model (AQSSPM). Methodology: Firstly, we identified 19 causes of challenging factors discussed in our previous study, which are potentially impacting agile-quantum project success. Secondly, a survey was conducted to collect expert opinions on these causes and applied Genetic Algorithm (GA) with Naive Bayes Classifier (NBC) and Logistic Regression (LR) to develop the AQSSPM. Results: Utilizing GA with NBC, project success probability improved from 53.17% to 99.68%, with cost reductions from 0.463% to 0.403%. Similarly, GA with LR increased success rates from 55.52% to 98.99%, and costs decreased from 0.496% to 0.409% after 100 iterations. Both methods result showed a strong positive correlation (rs=0.955) in causes ranking, with no significant difference between them (t=1.195, p=0.240>0.05). Conclusion: The AQSSPM highlights critical focus areas for efficiently and successfully implementing agile-quantum projects considering the cost factor of a particular project. © 2024, CC BY.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic geometric latent diffusion model for graph generation 24

Hyperbolic geometric latent diffusion model for graph genera...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xingcheng Fu Yisen Gao Yuecen Wei Qingyun Sun Hao Peng Jianxin Li Xianxian Li Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China and Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pareto Set Learning through Genetic Programming for Multi-Objective Dynamic Scheduling

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Xu, Meng Mei, Yi Zhang, Fangfang Ong, Yew Soon Zhang, Mengjie Agency for Science Technology and Research Singapore Institute of Manufacturing Technology Singapore Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Agency for Science Technology and Research College of Computing and Data Science Nanyang Technological University Centre for Frontier AI Research Institute of High Performance Computing Singapore Singapore

The multi-objective dynamic flexible job shop scheduling (MO-DFJSS) problem is crucial in modern manufacturing, impacting productivity and operational costs. Genetic Programming (GP) has emerged as a prominent method for MO-DFJSS due to its ability to evolve real-time responsible and effective scheduling heuristics. However, existing GP approaches often learn multiple heuristics for different regions of the Pareto front, making their management and selection complicated in real-world applications. This paper proposes a novel Pareto set learning GP (PSLGP) framework that addresses this limitation by learning a single, preference-conditioned heuristic that encompasses the entire Pareto front based on user preferences. This simplifies scheduling and allows for real-time adaptation to user-defined priorities. The framework employs a novel preference-conditioned heuristic representation that incorporates user preferences as additional inputs, enabling dynamic heuristic adjustments. To efficiently evaluate fitness without increasing training time, a surrogate model is used to estimate individual performance across different preferences, and three new fitness aggregation strategies are designed to ensure effective heuristic alignment across the Pareto front. Experimental results demonstrate that PSLGP significantly outperforms the state-of-the-art multi-objective GP approach, particularly in less busy MO-DFJSS environments, providing a more adaptable and efficient solution for dynamic scheduling challenges. Further analyses of preference influence, solution distribution, and heuristic structure provide evidence that the proposed PSLGP effectively learns preference-conditioned scheduling heuristics that align user preferences with various regions of the Pareto front. © 1997-2012 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce NAS Space for Heterogeneous Pipeline of CNNs

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Huijuan Duan Danghui Wang Xingting Zhao Kuizhi Mei Jihe Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

Efficiently deploying neural network models on heterogeneous edge systems faces unique challenges. Two major issues are underutilized pipelines caused by hardware heterogeneity and explosive growth of architecture search space. To address these challenges, we propose ExpoNAS, a framework enabling fast deployment-oriented neural architecture search on heterogeneous platforms. ExpoNAS evaluates model partitioning and deployability before search to meet accuracy and latency constraints. However, repeated partitioning leads to exponential growth in architecture search space. We first observe a strong correlation between operational exposure and accuracy improvement, and then we propose an exposure-based reduction technique that excludes the operations of low exposure. By removing these non-critical operations, the exposure-based pruning successfully reduces architecture search time. Our experiments on popular datasets show that the ExpoNAS pipelined design improves execution efficiency by a factor of 2 compared to traditional batch processing. Without compromising accuracy, ExpoNAS is able to reduce the architecture search time by 47.5% for discovering high-accuracy networks, compared to the SOTA NAS strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated 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：