检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Lin, Peijia Chen, Pin Jiao, Rui Mo, Qing Cen, Jianhuan Huang, Wenbing Liu, Yang Huang, Dan Lu, Yutong School of Computer Science and Engineering Sun Yat-sen University Guangzhou China National Supercomputer Center Guangzhou China Dept. of Comp. Sci. Tech. Institute for AI Tsinghua University Beijing China Institute for AIR Tsinghua University Beijing China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process. Code is available at https://***/EmperorJia/EquiCSP. Copyright 2024 by the author(s)

关键词： Crystal symmetry

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Lunar Landing Pad Designs and Construction Methods 6

An Analysis of Lunar Landing Pad Designs and Construction Me...

引用

6th International Conference on Additive Manufacturing, ICAM 2021

作者： Campbell, Andres I. Carson, Helen C. De Soto, Miriam Fiske, Michael R. Martin, Luke E. Murai, Vincent R.T. Ramirez, Fernanda S. Romo, Ethan M. Schang, Kayla E. Smith, Kaveon C. Dept. of Integrated Engineering Minnesota State University 227 Wissink Hall MankatoMN56001 United States Dept. of Materials Science and Engineering University of Washington 302 Roberts Hall Box 352120 SeattleWA98195 United States Engineering and Computer Science Dept. California State University Fullerton Fullerton 800 N. State College Blvd. FullertonCA92802 United States Advanced Materials and Manufacturing NASA/MSFC Space Technology Development Branch Jacobs Space Exploration Group Martin Rd. SW HuntsvilleAL35806 United States Dept. of Engineering Management Arizona State University 699 S Mill Ave. TempeAZ85281 United States Engineering Dept. University of Hawaii at Manoa 2540 Dole St. HonoluluHI96822 United States Engineering Dept. Santa Ana College 1530 W 17th St. Santa AnaCA92707 United States Physics Dept. University of California Santa Cruz 1156 High St. Santa CruzCA95064 United States Dept. of Physics University of Central Florida 4000 Central Florida Blvd. OrlandoFL32816 United States Dept. of Computer Science Oklahoma State University 218 MSCS Bldg. StillwaterOK74078 United States

ISBN: (纸本)9780803177352

Since the Apollo era, the debris-generating interactions between a rocket and extraterrestrial surfaces have caused known risks to large-scale lunar and planetary exploration. In situ resource utilization (ISRU) technology has the potential to solve this challenge by enabling the construction of 3D-printed landing and launch pads. This paper discusses past efforts and designs of these pads with a focus on material sintering and extrusion methods of additive construction. Proposals that are explored include tiles-based construction techniques, lunar regolith sintering methods, 3D architectures to control dust and exhaust plumes, and aerodynamically designed exterior structures. Developments in additive construction methods and materials are also discussed in the context of ISRU landing pad compatibility and potential design constraints. This paper analyzes the strengths and weaknesses of 11 concepts, providing insights into the design, construction, testing, and analysis of landing pad designs that are essential to realizing human habitation on the Moon. Copyright © 2022 by ASTM International.

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Deep Learning for Credit Card Fraud Detection: A Comparative Analysis

Machine Learning and Deep Learning for Credit Card Fraud Det...

引用

Artificial Intelligence and Emerging Technology (Global AI Summit), International Conference on

作者： Jyoti Komal Bhardwaj Garima Mukesh Kumar Rajit Verma Divyansh Kumar Computer Science dept. Govt. PG College for Women Rohtak Haryana India MM Institute of Management Maharishi Markandeshwar (Deemed to be University) Mullana Ambala Haryana Chitkara University Institute of Engineering and Technology Chitkara University India

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

Since last couple of the years, credit card frauds have been inclining abruptly. These frauds can be stated as the illicit usage of card, uncommon transaction activity, or swapping of an inert card. In other words, illegal account access by a person for which the account was not anticipated, is called as fraud and the process of behavior recognition of transactions known as authentic or deceptive. Detection of these frauds is truly the procedure of transactions classification i.e. authorized class and fraud class. Numerous techniques have been put forth and put into practice to address credit card fraud detection, including proposed and implemented to treat of credit card fraud detection like, data mining, nature-inspired algorithms like evolutionary algorithms & swarm techniques, machine learning algorithms etc. Machine Learning (ML) possess outstanding role in the uncovering frauds in online transactions. Fraudsters are becoming increasingly smarter and accustomed so there is a need of more robust, scalable and computationally efficient prediction models like Deep Neural Networks. Machine learning includes the subfield of deep learning, which is a more comprehensive use of artificial neural networks (ANN) that use several layers of non-linear processing components for feature mining as well as transformation. Deep learning is a sort of machine learning that helps computers understand the world through a conceptual hierarchy and learn from training. Therefore, a solution to lessening losses brought on by credit card fraud is to create efficient fraud detection algorithms utilizing machine learning, and more especially, deep learning approaches. In this study the use of deep learning and machine learning techniques to combat credit card fraud, have been compared. The results show that deep learning based approach overtakes all the other ML techniques with the utmost precision and can be effectually used for fraud investigation.

关键词： Deep learning Training Machine learning algorithms Computational modeling Artificial neural networks Credit cards Data models Fraud Classification algorithms Tuning

来源：评论

学校读者我要写书评

暂无评论

Impact of Demand and Supply in Decision Making for E-Commerce Application

Impact of Demand and Supply in Decision Making for E-Commerc...

引用

Advanced Computing & Communication Technologies (ICACCTech), International Conference on

作者： Pappu Kumar Rajak Alka Divya Tigga Veera Talukdar S Praveenkumar Arpit Namdev Ankur Gupta Dept. of Commerce Doranda College Ranchi Jharkhand India Dept. of Computer Science D Y Patil International University Akurdi Pune Maharashtra India Centre for Tourism and Hotel Management Madurai Kamaraj University Madurai TN India Dept. of IT University Institute of Technology RGPV Bhopal MP India Dept. of CSE Vaish College of Engineering Rohtak Haryana India

In the rapidly evolving realm of e-commerce, the equilibrium between demand and supply is a linchpin for operational success and financial viability. This abstract encapsulates the core challenge of optimizing decision-making processes within e-commerce applications to navigate the intricate landscape of supply and demand dynamics. With consumer preferences in a state of constant flux and market trends evolving at an unprecedented pace, the challenge lies in comprehending and responding adept.y to these fluctuations. The primary objective is to devise dynamic, analytics-driven decision-making frameworks that empower e-commerce platforms to optimize their demand and supply dynamics, simultaneously ensuring customer satisfaction and sustainable business growth. The stakeholders most affected by the efficacy of these strategies include e-commerce managers, supply chain professionals, and consumers, further emphasizing the urgency and relevance of this issue in the contemporary e-commerce landscape. In the current study, an Analysis of Variance (ANOVA) approach has been used to examine the potential influence of employment on high, moderate, and low levels of demand and supply. ANOVA, or analysis of variance, is a statistical method often used in workforce diversity research. Its purpose is to evaluate if there are statistically significant disparities in a certain outcome variable among various employee groups, as determined by their diversity characteristics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Differential Private Discrete Noise Adding Mechanism: Conditions, Properties and Optimization

arXiv

引用

arXiv 2022年

作者： Qin, Shuying He, Jianping Fang, Chongrong Lam, James The Dept. of Automation Shanghai Jiao Tong University The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China The Dept. of Mechanical Engineering The University of Hong Kong Pokfulam Road Hong Kong

Differential privacy is a standard framework to quantify the privacy loss in the data anonymization process. To preserve differential privacy, a random noise adding mechanism is widely adopted, where the trade-off between data privacy level and data utility is of great concern. The privacy and utility properties for the continuous noise adding mechanism have been well studied. However, the related works are insufficient for the discrete random mechanism on discretely distributed data, e.g., traffic data, health records. This paper focuses on the discrete random noise adding mechanisms. We study the basic differential privacy conditions and properties for the general discrete random mechanisms, as well as the trade-off between data privacy and data utility. Specifically, we derive a sufficient and necessary condition for discrete ∊-differential privacy and a sufficient condition for discrete (∊, δ)-differential privacy, with the numerical estimation of differential privacy parameters. These conditions can be applied to analyze the differential privacy properties for the discrete noise adding mechanisms with various kinds of noises. Then, with the differential privacy guarantees, we propose an optimal discrete ∊-differential private noise adding mechanism under the utility-maximization framework, where the utility is characterized by the similarity of the statistical properties between the mechanism's input and output. For this setup, we find that the class of the discrete noise probability distributions in the optimal mechanism is Staircase-shaped. Copyright © 2022, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Beyond bandit feedback in online multiclass classification 21

Beyond bandit feedback in online multiclass classification

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Dirk van der Hoeven Federico Fusco Nicolò Cesa-Bianchi Dept. of Computer Science Università degli Studi di Milano Italy Dept. of Computer Control and Management Engineering Sapienza Università di Roma Italy DSRC & Dept. of Computer Science Università degli Studi di Milano Italy

ISBN: (纸本)9781713845393

We study the problem of online multiclass classification in a setting where the learner's feedback is determined by an arbitrary directed graph. While including bandit feedback as a special case, feedback graphs allow a much richer set of applications, including filtering and label efficient classification. We introduce GAP-PLETRON, the first online multiclass algorithm that works with arbitrary feedback graphs. For this new algorithm, we prove surrogate regret bounds that hold, both in expectation and with high probability, for a large class of surrogate losses. Our bounds are of order $B\sqrt{\rho KT}$, where B is the diameter of the prediction space, K is the number of classes, T is the time horizon, and ρ is the domination number (a graph-theoretic parameter affecting the amount of exploration). In the full information case, we show that GAPPLETRON achieves a constant surrogate regret of order B2K. We also prove a general lower bound of order max {B2K, √T} showing that our upper bounds are not significantly improvable. Experiments on synthetic data show that for various feedback graphs our algorithm is competitive against known baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond bandit feedback in online multiclass classification

arXiv

引用

arXiv 2021年

作者： van der Hoeven, Dirk Fusco, Federico Cesa-Bianchi, Nicolò Dept. of Computer Science Università degli Studi di Milano Italy Dept. of Computer Control and Management Engineering Sapienza Università di Roma Italy DSRC Dept. of Computer Science Università degli Studi di Milano Italy

We study the problem of online multiclass classification in a setting where the learner’s feedback is determined by an arbitrary directed graph. While including bandit feedback as a special case, feedback graphs allow a much richer set of applications, including filtering and label efficient classification. We introduce Gappletron, the first online multiclass algorithm that works with arbitrary feedback graphs. For this new algorithm, we prove surrogate regret bounds that hold, both in expectation and with high probability, for a large class of surrogate losses. Our bounds are of order B√ρKT, where B is the diameter of the prediction space, K is the number of classes, T is the time horizon, and ρ is the domination number (a graph-theoretic parameter affecting the amount of exploration). In the full information case, we show that Gappletron achieves a constant surrogate regret of order B2K. We also prove a general lower bound of order max {B2K, √T} showing that our upper bounds are not significantly improvable. Experiments on synthetic data show that for various feedback graphs our algorithm is competitive against known baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Forecasting Breakdowns of Electric Motors of a Sugar Factory Using Machine Learning Methods

Forecasting Breakdowns of Electric Motors of a Sugar Factory...

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Nataliia Zaiets Nataliia Lutska Lidiia Vlasenko Andrii Zhyltsov dept. of Automation and Robotic Systems National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine dept. of Automation and Computer Technologies of Control Systems National University of Food Technologies Kyiv Ukraine dept. of Software Engineering and Cyber Security State University of Trade and Economics Kyiv Ukraine dept. of electromagnetic systems The Institute of Electrodynamics of the National Academy of Sciences of Ukraine Kyiv Ukraine

the paper demonstrates the process of developing mathematical models for identifying breakdowns of electric motors using machine learning methods. The authors have developed three mathematical models for identifying breakdowns of electric drives with a power of 55 kW, 1500 rpm on the example of sugar production: model for quadratic discriminant analysis; binary classification decision tree; feed-forward neural network model. The best structures and parameters of the models were determined by machine learning methods. The performance of the models on the training and test sets was more than 96% by F-score. It was proposed to use all three models independently for diagnosing breakdowns of electric drives, while the decision maker makes the final decision on the replacement or repair of electrical equipment. This approach is justified and effective because of the diversity of models. The developed models, except for assessing the state of the engine, can also be used for simulation modelling, forecasting, and serve as information support for process operators in organizing equipment maintenance. The availability of real-time information about the state of equipment in production will allow timely repair or replacement of equipment, thereby reducing the risks of stopping production and increasing the resource efficiency of technological processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis for Sales Forecasting Using Machine Learning: Leveraging Data-Driven Insights for Enhanced Business Planning and Decision-Making

Predictive Analysis for Sales Forecasting Using Machine Lear...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Jonardan Koner Shailesh Shivaji Deore S. Roja Kalyani Nilesh Sahastrabuddhe Prashant Kalshetti Anthony Rose NICMAR University Pune Department of Computer Engineering SSVPS Bapusaheb Shivajirao Deore College of Engineering Dhule Maharashtra Department of Computer Science Engineering and Applications Bharathidasan University Trichy-23 Dr. D. Y. Patil Institute of Management and Research Pimpri Pune Dept. of BBA Dr. D Y Patil Vidyapeeth Global Business School and Research Centre Pune Institute of Management and Entrepreneurship Development Pune Maharashtra India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Within the modern trade scene, leveraging prescient investigation for deal estimating has developed as a basic procedure for organizations pointing to optimize their decision-making forms. This consideration centres on the application of the XG Boost calculation, a well-known machine learning method, to tackle data-driven experiences for upgraded deals determining, thus encouraging prevalent commerce arranging. Through an in-dept. investigation of authentic deals information, the inquiry about illustrates the noteworthiness of consolidating machine learning strategies, especially the XG Boost calculation, for exact and solid deal forecasts. By leveraging a comprehensive dataset including different variables affecting deals, such as client socioeconomics, regular patterns, showcasing activities, and financial markets, this exhibits the algorithm's capability to capture complex connections inside the information and produce exact figures. Besides, the investigation emphasizes. interpretability of the XGBoost calculation, empowering partners to comprehend the fundamental components affecting deal expectations. This straightforwardness cultivates a more profound understanding of the driving powers behind deal patterns, encouraging educated decision-making and proactive commerce arranging.

关键词： Machine learning algorithms Decision making Machine learning Organizations Solids Prediction algorithms Planning Predictive analytics Forecasting Socioeconomics

来源：评论

学校读者我要写书评

暂无评论

Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics

arXiv

引用

arXiv 2022年

作者： Zheng, Tianqi You, Pengcheng Mallada, Enrique The Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD21218 United States The Dept. of Industrial Engineering and Management Peking University Beijing China

In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward constraints. Several algorithms rooted in sampled-based primal-dual methods have been recently proposed to solve this problem in policy space. However, such methods are based on stochastic gradient descent-ascent algorithms whose trajectories are connected to the optimal policy only after a mixing output stage that depends on the algorithm’s history. As a result, there is a mismatch between the behavioral policy and the optimal one. In this work, we propose a novel algorithm for constrained RL that does not suffer from these limitations. Leveraging recent results on regularized saddle-flow dynamics, we develop a novel stochastic gradient descent-ascent algorithm whose trajectories converge to the optimal policy almost surely. © 2022, CC BY.

关键词： Reinforcement 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：