检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yin, Ming Wang, Mengdi Wang, Yu-Xiang The Department of Electrical and Computer Engineering Princeton University United States The Halıcıoğlu Data Science Institute UC San Diego United States

This article reviews the recent advances on the statistical foundation of reinforcement learning (RL) in the offline and low-adaptive settings. We will start by arguing why offline RL is the appropriate model for almost any real-life ML problems, even if they have nothing to do with the recent AI breakthroughs that use RL. Then we will zoom into two fundamental problems of offline RL: offline policy evaluation (OPE) and offline policy learning (OPL). It may be surprising to people that tight bounds for these problems were not known even for tabular and linear cases until recently. We delineate the differences between worst-case minimax bounds and instance-dependent bounds. We also cover key algorithmic ideas and proof techniques behind near-optimal instance-dependent methods in OPE and OPL. Finally, we discuss the limitations of offline RL and review a burgeoning problem of low-adaptive exploration which addresses these limitations by providing a sweet middle ground between offline and online RL. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DeepSC-Edge: Scientific Corrosion Segmentation with Edge-Guided and Class-Balanced Losses

DeepSC-Edge: Scientific Corrosion Segmentation with Edge-Gui...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Biao Yin Nicholas Josselyn Thomas Considine John Kelley Berend Rinderspacher Robert Jensen James Snyder Ziming Zhang Elke Rundensteiner Department of Data Science Worcester Polytechnic Institute Worcester MA Department of Computer Science Worcester Polytechnic Institute Worcester MA Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA

Corrosion is a prevalent issue in numerous industrial fields, causing expenses nearing $3 trillion or 4% of the GDP annually with safety threats and environmental pollution. To timely qualify and validate new corrosion-inhibiting materials on a large scale, accurate and efficient corrosion assessment is crucial. Yet it is hindered by a lack of automatic tools for expert-level corrosion segmentation of material science experimental images. Developing such tools is challenging due to limited domain-valid data, image artifacts visually similar to corrosion, various corrosion morphology, strong class imbalance, and millimeter-precision corrosion boundaries. To help the community address these challenges, we curate the first expert-level segmentation annotations for a real-world image dataset [1] for scientific corrosion segmentation. In addition, we design a deep learning based model, called DeepSC-Edge that achieves guidance of ground-truth edge learning by adopting a novel loss that avoids over-fitting to edges. It also is enriched by integrating a class-balanced loss that improves segmentation with small area but crucial edges of interest for scientific corrosion assessment. Our dataset and methods pave the way to advanced deep-learning models for corrosion assessment and generation – promoting new research to connect computer vision and material science discovery. Once the appropriate approvals have been cleared, we expect to release the code and data at: https://***/

关键词：

来源：评论

学校读者我要写书评

暂无评论

A SAMPLE EFFICIENT ALTERNATING MINIMIZATION-BASED ALGORITHM FOR ROBUST PHASE RETRIEVAL

arXiv

引用

arXiv 2024年

作者： Barik, Adarsh Krishna, Anand Tan, Vincent Y.F. Institute of Data Science National University of Singapore Singapore117602 Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore Singapore119077 Singapore

In this work, we study the robust phase retrieval problem where the task is to recover an unknown signal θ∗ ∈ Rd in the presence of potentially arbitrarily corrupted magnitude-only linear measurements. We propose an alternating minimization approach that incorporates an oracle solver for a non-convex optimization problem as a subroutine. Our algorithm guarantees convergence to θ∗ and provides an explicit polynomial dependence of the convergence rate on the fraction of corrupted measurements. We then provide an efficient construction of the aforementioned oracle under a sparse arbitrary outliers model and offer valuable insights into the geometric properties of the loss landscape in phase retrieval with corrupted measurements. Our proposed oracle avoids the need for computationally intensive spectral initialization, using a simple gradient descent algorithm with a constant step size and random initialization instead. Additionally, our overall algorithm achieves nearly linear sample complexity, O(dpolylog(d)). Copyright © 2024, The Authors. All rights reserved.

关键词： Subroutines

来源：评论

学校读者我要写书评

暂无评论

3D Skull Completion via Two-stage Conditional Diffusion-Based Signed Distance Fields

3D Skull Completion via Two-stage Conditional Diffusion-Base...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Zhenhong Ru, Xudong Wang, Xingce Wu, Zhongke Zhu, Yi-Cheng Zhang, Chong Frangi, Alejandro F. Beijing Normal University School of Artificial Intelligence Beijing China Peking Union Medical College Hospital Department of Neurology Beijing China Bioimage Analysis Barcelona Spain School of Engineering University of Manchester Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences Department of Computer Science United Kingdom Department of Cardiovascular Sciences Department of Electrical Engineering Leuven Belgium Alan Turing Institute London United Kingdom

ISBN: (纸本)9798350386226

A fast and fully automatic design of 3D cranial implants is highly desired in cranioplasty, and is key to the treatment of skull trauma. We have defined the repair of skull defects as a 3D shape completion task by proposing a two-stage diffusion model based on the representation of 3D shapes using signed distance function (SDF). Specifically, we design a diffusion model conditioned on partial shapes, we compress the 3D shape into a compact latent representation using the encoder in the vector quantized variational autoencoder (VQ-VAE) and learn the diffusion model based on this compressed discrete representation. Encoding the latent space with the autoencoder can achieve high-quality 3D cranial shape completion. In order to accurately capture local and fine-grained shape details, the training data is geometrically encoded from a compactly learned code-book. The two-stage diffusion generator with a coarse-to-fine approach possesses precise and expressive structural modeling capabilities to ensure the supplementation of detailed geometric information. Experimental results verified sufficient expressiveness of our model with generating high-fidelity results with fine-grained local details, outperforming the state-of-the-art methods. © 2024 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Mitigating Translationese in Low-resource Languages: The Storyboard Approach 30

Mitigating Translationese in Low-resource Languages: The Sto...

引用

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

作者： Kuwanto, Garry Urua, Eno-Abasi Amuok, Priscilla Muhammad, Shamsuddeen Hassan Aremu, Anuoluwapo Otiende, Verrah Nanyanga, Loice Nyoike, Teresiah Akpan, Aniefon Udouboh, Nsima Archibong, Idongesit Moses, Idara Ige, Ifeoluwatayo Ajibade, Benjamin Awokoya, Olumide Abdulmumin, Idris Aliyu, Saminu Mohammad Iro, Ruqayya Ahmad, Ibrahim Said Smith, Deontae Michaels, Praise E.L. Adelani, David Ifeoluwa Wijaya, Derry Tanti Andy, Anietie Department of Computer Science Boston University United States University of Uyo Nigeria Imperial College London United Kingdom Rochester Institute of Technology United States Data Science for Social Impact Research Group University of Pretoria South Africa Bayero University Kano Nigeria Institute For Experiential AI Northeastern University United States Department of Electrical Engineering and Computer Science Howard University United States University College London United Kingdom Monash University Indonesia Indonesia Masakhane

ISBN: (纸本)9782493814104

Low-resource languages often face challenges in acquiring high-quality language data due to the reliance on translation-based methods, which can introduce the translationese effect. This phenomenon results in translated sentences that lack fluency and naturalness in the target language. In this paper, we propose a novel approach for data collection by leveraging storyboards to elicit more fluent and natural sentences. Our method involves presenting native speakers with visual stimuli in the form of storyboards and collecting their descriptions without direct exposure to the source text. We conducted a comprehensive evaluation comparing our storyboard-based approach with traditional text translation-based methods in terms of accuracy and fluency. Human annotators and quantitative metrics were used to assess translation quality. The results indicate a preference for text translation in terms of accuracy, while our method demonstrates worse accuracy but better fluency in the language focused. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

Cyberattacks against Direct Load Control of Residential Electric Water Heaters in Smart Grids

Cyberattacks against Direct Load Control of Residential Elec...

引用

2022 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2022

作者： Youssef, El-Nasser S. Labeau, Fabrice Kassouf, Marthe Alarie, Stéphane McGill University Department of Electrical and Computer Engineering MontrealQC Canada Hydro-Quebec's Research Institute Data Science and High Performance Computing Unit VarennesQC Canada

ISBN: (数字)9781665437752

ISBN: (纸本)9781665437752

The invasive deployment of digital technologies in power grids increases their exposure to cyber threats. In this paper, we study a type of load-altering cyberattack that targets peak shaving programs wherein a utility directly controls the loads of domestic electric water heaters. We consider a cyberattack scenario in which an adversary gains access to the advanced metering infrastructure and sends malicious activation commands to a large number of water heaters forcing them to simultaneously switch on in the midst of a peak shaving period, thus causing a sudden, large power demand that could lead to a system-wide blackout. We develop a simulation environment to simulate the loads of a population of electric water heaters under different operating conditions as well as under this type of cyberattack. Then, we propose a cybersecurity-by-design approach to mitigate the risk of such cyberattack. The efficacy of the proposed solution is analyzed using software experiments. © 2022 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

ONLINE ADVERSARIAL PURIFICATION BASED ON SELF-SUPERVISED LEARNING 9

ONLINE ADVERSARIAL PURIFICATION BASED ON SELF-SUPERVISED LEA...

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Shi, Changhao Holtz, Chester Mishne, Gal Department of Electrical and Computer Engineering Department of Computer Science and Engineering The Halıcıoğlu Data Science Institute University of California San Diego United States

Deep neural networks are known to be vulnerable to adversarial examples, where a perturbation in the input space leads to an amplified shift in the latent network representation. In this paper, we combine canonical supervised learning with self-supervised representation learning, and present Self-supervised Online Adversarial Purification (SOAP), a novel defense strategy that uses a self-supervised loss to purify adversarial examples at test-time. Our approach leverages the label-independent nature of self-supervised signals, and counters the adversarial perturbation with respect to the self-supervised tasks. SOAP yields competitive robust accuracy against state-of-the-art adversarial training and purification methods, with considerably less training complexity. In addition, our approach is robust even when adversaries are given knowledge of the purification defense strategy. To the best of our knowledge, our paper is the first that generalizes the idea of using self-supervised signals to perform online test-time purification. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Purification

来源：评论

学校读者我要写书评

暂无评论

Building Consensus in Group Decision-Making with Intuitionistic Reciprocal Preference Relations: An Analysis of Various Protocols of Information Granularity Distribution

Building Consensus in Group Decision-Making with Intuitionis...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Juan Carlos González-Quesada Francisco Javier Cabrerizo Enrique Herrera-Viedma Witold Pedrycz Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada Spain Department of Electrical & Computer Engineering University of Alberta Edmonton AB Canada

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

On the one hand, to model experts' preferences in group decision-making, intuitionistic reciprocal preference relations have widely been used because they allow for accommodating hesitation degrees, which are inherent to all decision-making processes. On the other hand, an optimization of information granularity distribution has recently been applied to establish consensus during group decision-making processes. Concretely, a symmetric and uniform distribution of information granularity has been considered for intuitionistic reciprocal preference relations. However, there exist other protocols of information granularity distribution that could be used. Therefore, we aim to analyze all the information granularity distribution protocols and determine their effectiveness in building consensus through intuitionistic reciprocal preference relations. The performance of the different protocols is discussed by conducting some numerical experiments that help provide insights into the effectiveness of the protocols to build consensus.

关键词： Hands Protocols Decision making Buildings Resource management Optimization Cybernetics

来源：评论

学校读者我要写书评

暂无评论

data Analytics for Core Temperature Estimation in Battery Management System for Electric and Hybrid Vehicles 5

Data Analytics for Core Temperature Estimation in Battery Ma...

引用

5th International Conference on Energy, Power, and Environment, ICEPE 2023

作者： Chhetri, Ahilya Surya, Sumukh Mohan Krishna, S. Rao, Vidya Cactus Communications Engineering and Technology Mumbai India Bosch Global Software Technologies Pvt. Limited Bengaluru India Aced Alliance University Department of Electrical and Electronics Engineering Bengaluru India Manipal Institute of Technology Manipal Academy of Higher Education Department of Data Science and Computer Applications Manipal India

ISBN: (纸本)9798350313123

Compared to conventional means of transport thatuse fossil fuels, electric vehicles are known to reduce pollution levels as they take power from renewable sources of energy stored in energy storage devices like batteries and fuel cells. Core temperature estimation of batteriesis extremely important inbattery management systems for preventing thermal runaway and ensuring safe operation. In this study, core temperature is estimated using a Kalman filter for two different battery chemistries viz;lithium polymer and lithium iron phosphate using a second-order thermal model. Further, a linear regression model is applied to verify the prediction over the trained and tested dataset. The lithium iron phosphate prediction curvehad a fit of approximately 82-83%, whilelithium polymerhad a fit of 72-82% during the charging and discharging of OCV-SOC variation. © 2023 IEEE.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Optimal Green Energy Estimation for Sustainable Electric Vehicle Networks Using Queueing-Based Retrial Process 1

Optimal Green Energy Estimation for Sustainable Electric Veh...

引用

1st International Conference on Sustainable Energy Technologies and Computational Intelligence, SETCOM 2025

作者： Varshney, Shreekant Raval, Jainit Priyadarshi, Rahul Manek, Vidhi Dadheech, Yash Shah, Manthan Pandit Deendayal Energy University School of Technology Department of Mathematics Gujarat Gandhinagar382426 India Pandit Deendayal Energy University School of Energy Technology Department of Electrical Engineering Gujarat Gandhinagar382426 India Symbiosis International University Symbiosis Institute of International Business Hinjewadi Maharashtra Pune411057 India New York University Center for Data Science Department of Center for Data Science New YorkNY United States Pandit Deendayal Energy University School of Technology Department of Computer Science and Engineering Gujarat Gandhinagar382426 India Pandit Deendayal Energy University School of Technology Department of Mechanical Engineering Gujarat Gandhinagar382426 India

ISBN: (纸本)9798331520540

This paper presents a stochastic model for addressing a single-server service station offering both EV charging and battery swapping services, considering the realistic retrial-based queueing behavior of the waiting individuals. A computationally efficient method is proposed for determining the steady-state probability distribution of the charging network. The approach involves analyzing the governing differential-difference equations and employing a matrix method to derive the steady-state probability distribution. Further, straightforward formulae are derived for critical system performance indicators, considering both server and system characteristics. Numerical results are visualized in the form of different graphical representations to demonstrate the influence of various parameters on system performance. Finally, the paper concludes with significant findings and future research directions to apprise researchers, decision-makers, and system designers in optimizing combined charging/swapping infrastructure. © 2025 IEEE.

关键词： Markov chains

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：