检索结果-内蒙古大学图书馆

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Jaron J. R. Lee AmirEmad Ghassami Ilya Shpitser Department of Computer Science Johns Hopkins University Baltimore Maryland Department of Mathematics and Statistics Boston University Boston Massachusetts

Identification of causal effects can be hampered by confounding, selection bias, and other complications. data fusion is one approach to addressing these difficulties, through the inclusion of auxiliary data on the population of interest. Such data may measure a different set of variables, or be obtained under different experimental or observational conditions than the primary dataset. In particular, selection of experimental units into different datasets may be systematic; similar difficulties are encountered in missing data problems. However, existing methods for combining datasets either do not consider this issue, or assume simple selection mechanisms. In this paper, we propose a general approach, based on graphical causal models, for causal inference from data on the same population that is obtained under different experimental conditions. Our framework allows both arbitrary unobserved confounding, and arbitrary selection processes into different experimental regimes in our data. We describe how systematic selection processes may be organized into a hierarchy similar to censoring processes in missing data: selected completely at random, selected at random, and selected not at random. Finally, we provide a novel general identification algorithm for interventional distributions in this setting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-probability sample complexities for policy evaluation with linear function approximation

arXiv

引用

arXiv 2023年

作者： Li, Gen Wu, Weichen Chi, Yuejie Ma, Cong Rinaldo, Alessandro Wei, Yuting The Department of Statistics The Chinese University of Hong Kong Hong Kong The Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States The Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA15213 United States The Department of Statistics University of Chicago ChicagoIL60637 United States The Department of Statistics and Data Science University of Texas at Austin Austin78712 United States The Department of Statistics and Data Science The Wharton School University of Pennsylvania PhiladelphiaPA19104 United States

This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation error of the best linear coefficients for two widely-used policy evaluation algorithms: the temporal difference (TD) learning algorithm and the two-timescale linear TD with gradient correction (TDC) algorithm. In both the on-policy setting, where observations are generated from the target policy, and the off-policy setting, where samples are drawn from a behavior policy potentially different from the target policy, we establish the first sample complexity bound with high-probability convergence guarantee that attains the optimal dependence on the tolerance level. We also exhibit an explicit dependence on problem-related quantities, and show in the on-policy setting that our upper bound matches the minimax lower bound on crucial problem parameters, including the choice of the feature map and the problem dimension. © 2023, CC BY.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Climate And Resource Awareness is Imperative to Achieving Sustainable AI (and Preventing a Global AI Arms Race)

arXiv

引用

arXiv 2025年

作者： Bakhtiarifard, Pedram Tözün, Pınar Igel, Christian Selvan, Raghavendra Department of Computer Science University of Copenhagen Denmark Data Systems & Robotics Section IT University of Copenhagen Denmark

Sustainability encompasses three key facets: economic, environmental, and social. However, the nascent discourse that is emerging on sustainable artificial intelligence (AI) has predominantly focused on the environmental sustainability of AI, often neglecting the economic and social aspects. Achieving truly sustainable AI necessitates addressing the tension between its climate awareness – the need to mitigate AI’s environmental impacts – and its social sustainability, which hinges on equitable access to AI development resources. The concept of resource awareness advocates for broader access to the infrastructure required to develop AI, fostering equity in AI innovation. Yet, this push for improving accessibility often overlooks the environmental costs of expanding such resource usage. In this position paper, we argue that reconciling climate and resource awareness is essential to realizing the full potential of sustainable AI. We use the framework of base-superstructure to analyze how the material conditions are influencing the current AI discourse. We also introduce the Climate and Resource Aware Machine Learning (CARAML) framework to address this conflict and propose actionable recommendations spanning individual, community, industry, government, and global levels to achieve sustainable AI. © 2025, CC BY.

关键词： Sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

Utilizing Machine Learning for Forecasting Profitable Vegetable Crops and Land Use in Sri Lankan Agriculture

Utilizing Machine Learning for Forecasting Profitable Vegeta...

引用

Artificial Intelligence (SLAAI-ICAI), SLAAI International Conference on

作者： S.A.H Nethmini W.A.C. Weerakoon Department of Statistics and Computer Science University of Kelaniya Kelaniya Sri Lanka

The agriculture sector faces numerous challenges, such as the selection of profitable vegetable crops, the reduction of surplus vegetable stocks, and the minimization of product losses in various vegetable varieties. This research study aims to address these challenges by employing machine learning to predict the most profitable vegetable crop and the corresponding land area required for cultivation. This anal-ysis considers multiple factors, including weather conditions, cultivation expenses, seasons, location, production data, and historical crop cultivation data. Multiple machine learning algorithms were employed to develop accurate crop prediction models namely, random forest RF, multinomial logistic regression MLR, and Long Short-Term Memory LSTM. The results indicate that multinomial logistic regression archives a higher accuracy of 0.84 for crop prediction and the random forest algorithm gives an accuracy of 0.83. The LSTM model demonstrated an R2score of 0.831. The model outputs the most profitable crop, which serves as input for the land extent prediction system. The application predicts the required land area for selected crops using RFR and LR. RFR gives a higher R2score of 0.956, indicating its superior fit to the data while the LR model achieved an R2score of 0.45. The root mean squared error of the RFR was 23.95 whereas the LR model had 89.29. The findings of this research study provide valuable information like crops and land extent to be cultivated in a particular area to increase productivity. The impact of this work extends to enhancing food security and reducing poverty in Sri Lanka by allowing farmers with the tools and knowledge to make correct decisions at the correct time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securing Consumer IoT Swarms Using Graph Transformers and SRAM for Firmware Attestation 22

Securing Consumer IoT Swarms Using Graph Transformers and SR...

引用

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Kohli, Varun Kohli, Bhavya Aman, Muhammad Naveed Sikdar, Biplab National University of Singapore Department of Electrical and Computer Engineering Singapore Center for Machine Intelligence and Data Science Indian Institute of Technology Bombay India School of Computing University of Nebraska-Lincoln United States

ISBN: (纸本)9798331508050

Consumer Internet of Things (IoT) networks have gained widespread popularity due to their convenience, automation, and security provisions in personal and home environments. Ubiquitous resource-constrained devices, however, are plagued with security issues that often arise from firmware-related issues and their propagated effects. While various studies on firmware attestation are available, they require firmware copies, specific hardware, and complex computation on the IoT device. This paper presents a study on the application of Graph Transformer Networks (GTN) in verifying the firmware integrity of consumer IoT swarms using SRAM as an attestation feature. The proposed method achieves an overall 0.99 accuracy on authentic samples from development and physical twin networks, 0.99 on malware, and 0.97 on propagated misbehavior at a ∼ 10-4 second inference latency on a laptop CPU. © 2025 IEEE.

关键词： computer viruses

来源：评论

学校读者我要写书评

暂无评论

Residual Connections Harm Generative Representation Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Xiao Jiang, Ruoxi Gao, William Willett, Rebecca Maire, Michael Department of Computer Science The University of Chicago Chicago United States Department of Statistics The University of Chicago Chicago United States

We show that introducing a weighting factor to reduce the influence of identity shortcuts in residual networks significantly enhances semantic feature learning in generative representation learning frameworks, such as masked autoencoders (MAEs) and diffusion models. Our modification notably improves feature quality, raising ImageNet-1K K-Nearest Neighbor accuracy from 27.4% to 63.9% and linear probing accuracy from 67.8% to 72.7% for MAEs with a ViT-B/16 backbone, while also enhancing generation quality in diffusion models. This significant gap suggests that, while residual connection structure serves an essential role in facilitating gradient propagation, it may have a harmful side effect of reducing capacity for abstract learning by virtue of injecting an echo of shallower representations into deeper layers. We ameliorate this downside via a fixed formula for monotonically decreasing the contribution of identity connections as layer depth increases. Our design promotes the gradual development of feature abstractions, without impacting network trainability. Analyzing the representations learned by our modified residual networks, we find correlation between low effective feature rank and downstream task performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Multi-Block Deep CNN 5

Facial Expression Recognition Using Multi-Block Deep CNN

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Priyadarshini, V. Srinivasulu Reddy, U. Reddy Chirra, Venkata Rami Mrudula, M. Suneetha, M. National Institute of Technology Dept. of Computer Science & Engineering Andhra Pradesh India Machine Learning & Data Analytics Lab National Institute of Technology Dept. of Computer Applications Tiruchirappalli India School of Computer Science & Engineering VIT-AP University Amaravathi India Malla Reddy College of Engineering Department of CSE Telangana India Independent Researcher Amaravati India

ISBN: (纸本)9798331528539

Emotions play a crucial role in decision-making, moral judgments, and other cognitive processes. The goal of this work is to identify people's facial emotions from face images. Facial expression recognition (FER), a highly diverse field with many commonalities between classes, is a challenging problem. The capabilities of current FER systems are limited in this regard. In this work, a multi-block Deep Convolutional Neural Networks (DCNN) model was proposed to identify facial expressions. Five blocks with different computational components were defined in a multi-block DCNN to extract the unique characteristics from input images. The second model (DCNN-SVM) is developed with an ensemble of SVM classifier to improve predictability and stability. The third model (DCNN-MV) is based on the majority voting with 4 classifiers SVM, KNN, Random Forest, and Decision Tree. The CK+ dataset was utilized and expanded via image data augmentation to enhance model performance and generalization. By adjusting hyperparameters, the suggested DCNN model's accuracy was investigated. The DCNN model reports an accuracy score of 97.71%. Both DCNN-SVM and DCNN-MV models achieved 97.79% accuracy. On the CK+ dataset, the proposed models demonstrated good accuracy in identifying facial expressions. When compared to existing models, the proposed model outperformed existing models in terms of accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Accelerating Medical Knowledge Discovery Through Automated Knowledge Graph Generation and Enrichment 6th

Accelerating Medical Knowledge Discovery Through Automated K...

引用

6th International Conference on Knowledge Graphs and Semantic Web, KGSWC 2024

作者： Khalid, Mutahira Rahman, Raihana Abbas, Asim Kumari, Sushama Wajahat, Iram Bukhari, Syed Ahmad Chan TIB - Leibniz Information Centre for Science and Technology Lower Saxony Hannover30165 Germany Department of Statistics Harvard University CambridgeMA United States School of Computer Science University of Birmingham Edgbaston Birmingham United Kingdom Routing and Planning Amazon BellevueWA United States Institute for Biotechnology St. John’s University New York United States Division of Computer Science Mathematics and Science St. John’s University New York United States

ISBN: (纸本)9783031812200

Knowledge graphs (KGs) serve as powerful tools for organizing and representing structured knowledge. While their utility is widely recognized, challenges persist in their automation and completeness. Despite efforts in automation and the utilization of expert-created ontologies, gaps in connectivity remain prevalent within KGs. In response to these challenges, we propose an innovative approach termed "Medical Knowledge Graph Automation (M-KGA)". M-KGA leverages user-provided medical concepts and enriches them semantically using BioPortal ontologies, thereby enhancing the completeness of knowledge graphs through the integration of pre-trained embeddings. Our approach introduces two distinct methodologies for uncovering hidden connections within the knowledge graph: a cluster-based approach and a node-based approach. Through rigorous testing involving 300 frequently occurring medical concepts in Electronic Health Records (EHRs), our M-KGA framework demonstrates promising results obtained 50% accuracy, 57% F1-score, 50% recall and 65% precision on a cluster base approach. Similarly, we achieve 85% accuracy, 87% F1-score, 89% recall and 88% precision on a node base approach indicating its potential to address the limitations of existing knowledge graph automation techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Optimal Physician Shared-Patient Networks and the Diffusion of Medical Technologies

引用

Journal of data science 2023年第3期21卷 578-598页

作者： Ran, Xin An, Chuankai Rockmore, Daniel N. Department of Biomedical Data Science The Dartmouth Institute for Health Policy and Clinical Practice Geisel School of Medicine at Dartmouth Lebanon 03756 NH United States Department of Biomedical Data Science The Dartmouth Institute for Health Policy and Clinical Practice and the Program in Quantitative Biomedical Sciences Geisel School of Medicine at Dartmouth Lebanon 03756 NH United States Research Institute of China Investment Corporation Beijing 100010 China Department of Mathematics Department of Computer Science Hanover 03755 NH United States The Santa Fe Institute Santa Fe 87501 NM United States

Social network analysis has created a productive framework for the analysis of the histories of patient-physician interactions and physician collaboration. Notable is the construction of networks based on the data of "referral paths"- sequences of patient-specific temporally linked physician visits - in this case, culled from a large set of Medicare claims data in the United States. Network constructions depend on a range of choices regarding the underlying data. In this paper we introduce the use of a five-factor experiment that produces 80 distinct projections of the bipartite patient-physician mixing matrix to a unipartite physician network derived from the referral path data, which is further analyzed at the level of the 2,219 hospitals in the final analytic sample. We summarize the networks of physicians within a given hospital using a range of directed and undirected network features (quantities that summarize structural properties of the network such as its size, density, and reciprocity). The different projections and their underlying factors are evaluated in terms of the heterogeneity of the network features across the hospitals. We also evaluate the projections relative to their ability to improve the predictive accuracy of a model estimating a hospital's adoption of implantable cardiac defibrillators, a novel cardiac intervention. Because it optimizes the knowledge learned about the overall and interactive effects of the factors, we anticipate that the factorial design setting for network analysis may be useful more generally as a methodological advance in network analysis. © 2023 The Author(s).

关键词： bipartite network directional information factorial design implantable cardiac defibrillators optimal bipartite-unipartite projection shared-patient physician network

来源：评论

学校读者我要写书评

暂无评论

Predicting Crops Based on Soil and Environmental Characteristics Using ARIMA and LSTM Model 4

Predicting Crops Based on Soil and Environmental Characteris...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Naresh Kumar, U. Madhana Mohan, K. Pragadeeswaran, S. Scaria, Jobin M. Baseera, A. Seenivasan, D. Annamacharya University Department of Artificial intelligence & Data science Rajampet India Sri Sairam Engineering College Department of Electronics and Instrumentation Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Cse Chennai India School of Information Technology Ibs University Mt. Eriama Campus Port Moresby Papua New Guinea School of Computing Science and Engineering Vit Bhopal University Sehore India M. Kumarasamy College of Engineering Department of Computer Science and Business Systems Karur India

ISBN: (纸本)9798350352931

Food producers are under pressure to meet rising demand as the world's population and natural resources diminish. Overuse of pesticides and fertilizers has caused soil erosion and land degradation. Future food needs will require environmentally sustainable farming strategies. The suggested strategy includes model training, feature extraction, sensor integration, and model preparation. data preparation involves processing data before storing it machine-readable. SFFS and RFE select features. The model was trained using a hybrid ARIMA-LSTM technique, which blends deep learning and time-series forecasting. The ARIMA-LSTM model outperforms solo ARIMA and LSTM models with an average accuracy of 93.54%. Increased accuracy shows the model's capacity to anticipate sustainable agriculture approaches. data-driven and environmentally sustainable ways are needed to overcome global food production concerns, according to this study. When paired with good preprocessing and feature selection, ARIMA-LSTM can boost agricultural productivity while minimizing environmental impact. © 2024 IEEE.

关键词： crop productivity long short-term memory (lstm) soil management

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：