检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Mortier, Thomas Javanmardi, Alireza Sale, Yusuf Hüllermeier, Eyke Waegeman, Willem Department of Environment Ghent University Ghent Belgium Department of Data Analysis and Mathematical Modelling Ghent University Ghent Belgium Institute of Informatics LMU Munich Munich Germany Munich Center for Machine Learning Munich Germany

Conformal prediction has emerged as a widely used framework for constructing valid prediction sets in classification and regression tasks. In this work, we extend the split conformal prediction framework to hierarchical classification, where prediction sets are commonly restricted to internal nodes of a predefined hierarchy, and propose two computationally efficient inference algorithms. The first algorithm returns internal nodes as prediction sets, while the second relaxes this restriction, using the notion of representation complexity, yielding a more general and combinatorial inference problem, but smaller set sizes. Empirical evaluations on several benchmark datasets demonstrate the effectiveness of the proposed algorithms in achieving nominal coverage. © 2025, CC BY.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

MambaLRP: Explaining Selective State Space Sequence Models 38

MambaLRP: Explaining Selective State Space Sequence Models

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jafari, Farnoush Rezaei Montavon, Grégoire Müller, Klaus-Robert Eberle, Oliver Machine Learning Group Technische Universität Berlin Berlin10587 Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany Department of Mathematics and Computer Science Freie Universität Berlin Arnimallee 14 Berlin14195 Germany Department of Artificial Intelligence Korea University Seoul136-713 Korea Republic of Max Planck Institute for Informatics Stuhlsatzenhausweg 4 Saarbrücken66123 Germany Google DeepMind Berlin Germany

Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing of long sequences in linear time and are rapidly being adopted in a wide range of applications such as language modeling, demonstrating promising performance. To foster their reliable use in real-world scenarios, it is crucial to augment their transparency. Our work bridges this critical gap by bringing explainability, particularly Layer-wise Relevance Propagation (LRP), to the Mamba architecture. Guided by the axiom of relevance conservation, we identify specific components in the Mamba architecture, which cause unfaithful explanations. To remedy this issue, we propose MambaLRP, a novel algorithm within the LRP framework, which ensures a more stable and reliable relevance propagation through these components. Our proposed method is theoretically sound and excels in achieving state-of-the-art explanation performance across a diverse range of models and datasets. Moreover, MambaLRP facilitates a deeper inspection of Mamba architectures, uncovering various biases and evaluating their significance. It also enables the analysis of previous speculations regarding the long-range capabilities of Mamba models. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimating fish weight growth in aquaponic farming through machine learning techniques

Estimating fish weight growth in aquaponic farming through m...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Purushottam Kumar Pranav Tiwari U Srinivasulu Reddy CoE in Artificial Intelligence Machine Learning & Data Analytics Lab National Institute of Technology Trichy India Computer Science and Engineering Indian Institute of Information Technology Tiruchirappalli Trichy India Department of Computer Applications Machine Learning & Data Analytics Lab National Institute of Technology Trichy India

Due to the ever-growing population, rapid urbanization, unusual environmental change, and dwindling water supply, the food production from conventional farming techniques won’t be able to keep up with increasing food demand for long, leading to severe food scarcity. Aquaponics is emerging as a viable alternative to food cultivation techniques but lacks efficiency, hindering its adoption on a large-scale production basis. The adoption of Artificial Intelligence (AI) techniques in smart aquaponic farming can further contribute to increasing the yield in aquaponics. In the study, both linear and non-linear regression algorithms such as linear regression, lasso regression, ridge regression, KNN regression, SVR, and decision tree regression were trained on aquaponic fish pond dataset, evaluated on the basis of multiple metrics like MAE, MSE, RMSE, and RMSLE, and a competitive analysis was done to determine the best algorithm for predicting the harvest weight of the fish in aquaponic ponds. The results showed that KNN regression and decision tree regression algorithms have lowest error and highest accuracy of 99.15% and 99.1% respectively, for predicting the harvest weight of the fish. The results obtained could be scaled up to commercial levels and used in regulating nutrient concentration and aquatic environmental conditions

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Highly Efficient Anomaly Detection for Predictive Maintenance

Towards Highly Efficient Anomaly Detection for Predictive Ma...

引用

International Conference on machine learning and Applications (ICMLA)

作者： Simon Klüttermann Vanlal Peka Philipp Doebler Emmanuel Müller TU Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany Research Center Trustworthy Data Science and Security Dortmund Germany

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

This paper introduces SEAN, a novel anomaly detection algorithm designed for real-time applications in predictive maintenance. SEAN leverages an ensemble-based approach to deliver competitive performance while drastically reducing computational costs. In our comprehensive evaluation across 121 datasets, SEAN consistently outperforms comparable shallow anomaly detection algorithms. Our comparisons reveal that SEAN operates over 20,000 times faster than a similar state-of-the-art deep learning alternative, with negligible sacrifice in detection accuracy. We further demonstrate SEAN's versatility through an ablation study, highlighting how its hyperparameters can be tuned to balance runtime and performance effectively. Additionally, we present a practical C++ export tool that enables the deployment of SEAN on resource-constrained devices, meeting the stringent requirements of on-device predictive maintenance tasks. Our findings underscore SEAN as a powerful and efficient solution for anomaly detection in real-world engineering applications.

关键词： Performance evaluation Accuracy Runtime C++ languages Prediction algorithms Real-time systems Computational efficiency Time factors Anomaly detection Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

An Improved Finite-time Analysis of Temporal Difference learning with Deep Neural Networks

arXiv

引用

arXiv 2024年

作者： Ke, Zhifa Wen, Zaiwen Zhang, Junyu Center for Data Science Peking University China Beijing International Center for Mathematical Research Center for Machine Learning Research Changsha Institute for Computing and Digital Economy Beijing China Department of Industrial Systems Engineering and Management National University of Singapore Singapore

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these algorithms remains challenging due to the nonlinearity of the action-value approximation. In this paper, we develop an improved non-asymptotic analysis of the neural TD method with a general L-layer neural network. New proof techniques are developed and an improved new Õ(ϵ−1) sample complexity is derived. To our best knowledge, this is the first finite-time analysis of neural TD that achieves an Õ(ϵ−1) complexity under the Markovian sampling, as opposed to the best known Õ(ϵ−2) complexity in the existing literature. Copyright © 2024, The Authors. All rights reserved.

关键词： Asymptotic analysis

来源：评论

学校读者我要写书评

暂无评论

An improved finite-time analysis of temporal difference learning with deep neural networks 24

An improved finite-time analysis of temporal difference lear...

引用

Proceedings of the 41st International Conference on machine learning

作者： Zhifa Ke Zaiwen Wen Junyu Zhang Center for Data Science Peking University China Beijing International Center for Mathematical Research Center for Machine Learning Research and Changsha Institute for Computing and Digital Economy Beijing China Department of Industrial Systems Engineering and Management National University of Singapore Singapore

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these algorithms remains challenging due to the nonlinearity of the action-value approximation. In this paper, we develop an improved nonasymptotic analysis of the neural TD method with a general L-layer neural network. New proof techniques are developed and an improved new Õ(ε-1) sample complexity is derived. To our best knowledge, this is the first finite-time analysis of neural TD that achieves an Õ(ε-1) complexity under the Markovian sampling, as opposed to the best known Õ(ε-2) complexity in the existing literature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electricity Cost Minimization for Multi-Workflow Allocation in Geo-Distributed data Centers

引用

IEEE Transactions on Services Computing 2025年

作者： Wang, Shuang Zhang, He Wu, Tianxing Zhang, Yueyou Zhang, Wei Emma Sheng, Quan Z. Southeast University School of Computer Science and Engineering Nanjing211189 China The University of Adelaide School of Computer and Mathematical Sciences Australian Institute for Machine Learning Australia Macquarie University School of Computing SydneyNSW2109 Australia

Worldwide, Geo-distributed data Centers (GDCs) provide computing and storage services for massive workflow applications, resulting in high electricity costs that vary depending on geographical locations and time. How to reduce electricity costs while satisfying the deadline constraints of workflow applications is important in GDCs, which is determined by the execution time of servers, power, and electricity price. Determining the completion time of workflows with different server frequencies can be challenging, especially in scenarios with heterogeneous computing resources in GDCs. Moreover, the electricity price is also different in geographical locations and may change dynamically. To address these challenges, we develop a geo-distributed system architecture and propose an Electricity Cost aware Multiple Workflows Scheduling algorithm (ECMWS) for servers of GDCs with fixed frequency and power. ECMWS comprises four stages, namely workflow sequencing, deadline partitioning, task sequencing, and resource allocation where two graph embedding models and a policy network are constructed to solve the Markov Decision Process (MDP). After statistically calibrating parameters and algorithm components over a comprehensive set of workflow instances, the proposed algorithms are compared with the state-of-the-art methods over two types of workflow instances. The experimental results demonstrate that our proposed algorithm significantly outperforms other algorithms, achieving an improvement of over 15% while maintaining an acceptable computational time. The source codes are available at https://***/public-artifacts/ecmws-experiments. © 2025 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Light Weight Symmetric Encryption Algorithms for Secure data Transmission in IoT

An Analysis of Light Weight Symmetric Encryption Algorithms ...

引用

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

作者： Sanjay Kumar C. S. Pillai Department of CSE (Artificial Intelligence & Machine Learning) Don Bosco Institute of Technology Bengaluru India Department of CSE-Data Science ACS College of Engineering Bengaluru India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

The Internet of Things (IoT) consists of a network of resource-constrained devices, sensors, and machines that are interconnected and communicate via the internet. However, these devices often struggle while handling complex attacks during data encryption and after the encrypted data is transmitted. Cipher algorithms are therefore critical to the data security process because they handle the growing complexities in the applications of data environments. This review aims to present the most effective and efficient symmetric cipher algorithms, which use the same components as the ciphers. It demonstrates how the current cipher has developed into a lightweight encryption by lowering the number and impact of each component. Thus, it becomes clearer how the strength of these components varies between symmetric and asymmetric ciphers dependent on their size. Finally, several efficient lightweight symmetric cipher algorithms are selected, and the security, performance, and resource needs of each algorithm's components are reviewed.

关键词： Ciphers Reviews Encryption Sensors Complexity theory Internet of Things data communication Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

CENTRAL LIMIT THEOREMS FOR SMOOTH OPTIMAL TRANSPORT MAPS

arXiv

引用

arXiv 2023年

作者： Manole, Tudor Balakrishnan, Sivaraman Niles-Weed, Jonathan Wasserman, Larry Statistics and Data Science Center Massachusetts Institute of Technology United States Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States Center for Data Science New York University United States Courant Institute of Mathematical Sciences New York University United States

One of the central objects in the theory of optimal transport is the Brenier map: the unique monotone transformation which pushes forward an absolutely continuous probability law onto any other given law. A line of recent work has analyzed L2 convergence rates of plugin estimators of Brenier maps, which are defined as the Brenier map between density estimators of the underlying distributions. In this work, we show that such estimators satisfy a pointwise central limit theorem when the underlying laws are supported on the flat torus of dimension d ≥ 3. We also derive a negative result, showing that these estimators do not converge weakly in L2 when the dimension is sufficiently large. Our proofs hinge upon a quantitative linearization of the Monge-Ampère equation, which may be of independent interest. This result allows us to reduce our problem to that of deriving limit laws for the solution of a uniformly elliptic partial differential equation with a stochastic right-hand side, subject to periodic boundary conditions. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Digital Halftoning via Mixed-Order Weighted Σ∆ Modulation

Digital Halftoning via Mixed-Order Weighted Σ∆ Modulation

引用

International Conference on Sampling Theory and Applications (SampTA)

作者： Felix Krahmer Anna Veselovska Dept. of Mathematics & Munich Data Science Institute Technical University of Munich and Munich Center for Machine Learning Garching/Munich Germany

In this paper, we propose 1-bit weighted Σ∆ quantization schemes of mixed order as a technique for digital halftoning. These schemes combine weighted Σ∆ schemes of different orders for two-dimensional signals so one can profit both from the better stability properties of low order schemes and the better accuracy properties of higher order schemes. We demonstrate that the resulting mixed-order Σ∆ schemes in combination with a padding strategy yield improved representation quality in digital halftoning as measured in the Feature Similarity *** empirical results are complemented by mathematical error bounds for the model of two-dimensional bandlimited signals as motivated by a mathematical model of human visual perception.

关键词：

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：