检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2024年第1期25卷 4181-4226页

作者： Ricardo Baptista Rebecca Morrison Olivier Zahm Youssef Marzouk Department of Computing and Mathematical Sciences California Institute of Technology Pasadena CA Department of Computer Science University of Colorado Boulder Boulder CO Université Grenoble Alpes Inria CNRS Grenoble INP LJK Grenoble France Center for Computational Science and Engineering Massachusetts Institute of Technology Cambridge MA

Undirected probabilistic graphical models represent the conditional dependencies, or Markov properties, of a collection of random variables. Knowing the sparsity of such a graphical model is valuable for modeling multivariate distributions and for efficiently performing inference. While the problem of learning graph structure from data has been studied extensively for certain parametric families of distributions, most existing methods fail to consistently recover the graph structure for non-Gaussian data. Here we propose an algorithm for learning the Markov structure of continuous and non-Gaussian distributions. To characterize conditional independence, we introduce a score based on integrated Hessian information from the joint log-density, and we prove that this score upper bounds the conditional mutual information for a general class of distributions. To compute the score, our algorithm sing estimates the density using a deterministic coupling, induced by a triangular transport map, and iteratively exploits sparse structure in the map to reveal sparsity in the graph. For certain non-Gaussian datasets, we show that our algorithm recovers the graph structure even with a biased approximation to the density. Among other examples, we apply sing to learn the dependencies between the states of a chaotic dynamical system with local interactions.

关键词： undirected graphical models structure learning non-Gaussian distributions conditional mutual information transport map sparsity

来源：评论

学校读者我要写书评

暂无评论

DMNER: Biomedical Named Entity Recognition by Detection and Matching

DMNER: Biomedical Named Entity Recognition by Detection and ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Bian, Junyi Jiang, Rongze Zhai, Weiqi Huang, Tianyang Huang, Xiaodi Zhou, Hong Zhu, Shanfeng Fudan University School of Computer Science Shanghai China Fudan University Institute of Science and Technology for Brain-Inspired Intelligence Shanghai China Charles Sturt University School of Computing Mathematics and Engineering Nsw Australia Atypon Systems Llc United Kingdom Zhangjiang Fudan International Innovation Center Fudan University Institute of Science and Technology for Brain-Inspired Intelligence Moe Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Shanghai China

ISBN: (纸本)9798350386226

Biomedical Named Entity Recognition (NER) is a crucial task in extracting information from biomedical texts. However, the diversity of professional terminology, semantic complexity, and the widespread presence of synonyms pose significant challenges. Traditional methods that rely on sequence labeling training datasets often struggle to handle these complexities. To address this, we introduce a novel framework for BioNER, termed DMNER, which leverages external knowledge and operates in two steps: entity boundary detection and entity category identification through matching. The core of DMNER is its second step, which determines the entity category by retrieving similar entities and their categories from a knowledge dictionary using semantic similarity matching. Our experiments on 10 biomedical datasets demonstrate that DMNER outperforms baselines across these tasks, proving its effectiveness and adaptability. DMNER is versatile and can be applied to various NER tasks, including supervised NER, distantly supervised NER, and NER on multiple datasets with disjoint label sets. The DMNER code is publicly available. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

FPGA based Power Efficient Approximate 4:2 Compressor for Multimedia Applications 2

FPGA based Power Efficient Approximate 4:2 Compressor for Mu...

引用

2nd International Conference on Edge computing and Applications, ICECAA 2023

作者： Dinesh, G. Arunkumar, K. Radhakrishnan, P. Jadhav, Rajendra D. Dasari, Twinkle Lal, Hasamukh School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Saveetha Engineering College Department of Ece Chennai India Tagore Engineering College Department of Ece Chennai India Institute of Management Kolhapur India Koneru Lakshmaiah Education Foundation Department of Engineering English Andhra Pradesh Vaddeswaram India Ies University Department of Agriculture Sciences M.P Bhopal India

ISBN: (纸本)9798350347579

Approximate computing plays a crucial part in error resilent and multimedia applications. This study presents the design and analysis of a 4:2 compressor that employs a Dadda multiplier to reduce output power and inaccuracy. The approximate compressors are utilized to design 8∗8, 16∗16,32∗32 multipliers. The goal of this work is to develop a compressor with low latency, low power consumption, and fewer product stages. By reducing the number of transistors and gates the low latency compressors used to serve as multiplier design applications. The adders and product stages are to be considerable power consumption in multiplication process. The reduced compressors consume less power and it could be applicable for designers. © 2023 IEEE.

关键词： Compressors

来源：评论

学校读者我要写书评

暂无评论

Leveraging Instruction-based Learning for Effective UAV Traffic Management in Dynamic Environment

Leveraging Instruction-based Learning for Effective UAV Traf...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： R.S. Ramya Keren Lois Daniel S. Rajkumar Sruthi S Madhavan Akshya. J Mani Deepak Choudhry Department of Computer Science and Engineering Sri Ramakrishna Engineering College Coimbatore Department of Computer Science and Business Systems KGiSL Institute of Technology Coimbatore Department of Information Technology Sona College of Technology Salem Department of Artificial Intelligence and Data Science Nehru Institute of Engineering and Technology Coimbatore Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

With the popularization of UAVs (Unmanned Aerial Vehicles) in surveillance, delivery services, environmental monitoring, and increasingly other operational aspects, besides the need to take off and land, efficient traffic management becomes integral for assuring and securing further development and exploitation. Most of the existing traffic management systems for UAVs depend on traditional rule-based algorithms or simpler machine learning techniques, such as DQN or PPO. However, these systems also have enormous challenges: dynamic environments, high-density traffic, and robust decision-making over unpredictable weather and network conditions. In addition, the above traditional models usually experience difficulties in balancing exploration and exploitation, leading to suboptimal routing and enlarged collision risks in complicated urban airspaces. These challenges have driven us to develop a new proposal: a UA V traffic management framework based on Double Deep Q-Network (DDQN) combined with Instruction-Based Learning. In this approach, advanced learning for DDQN optimizes processes at decision-making points for UAVs. The model proposed herein, along with comprehensive simulations and quantitative analyses, demonstrated higher performance in terms of leadership and cumulative rewards while keeping lower training loss compared to the classical algorithms such as DQN, A3C, and PPO. At the same time, the DDQN model presented a better success rate (95%), as also reflected in the balanced precision-recall curve showing an area under the curve of 0.90, over others in the on-point prediction of UAVstate and safety margin of collision. Our experimental results demonstrate that the proposed DDQN-based framework significantly enhances UA V traffic management by optimizing energy consumption in complex airspaces and reducing the risk of collision.

关键词： Training Analytical models Adaptation models Statistical analysis Atmospheric modeling computational modeling Decision making Predictive models Autonomous aerial vehicles Safety

来源：评论

学校读者我要写书评

暂无评论

LEAST H2 NORM UPDATING QUADRATIC INTERPOLATION MODEL FUNCTION FOR DERIVATIVE-FREE TRUST-REGION ALGORITHMS

arXiv

引用

arXiv 2023年

作者： Xie, Pengcheng Yuan, Ya-Xiang Institute of Computational Math and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences University of Chinese Academy of Sciences China

Derivative-free optimization methods are numerical methods for optimization problems in which no derivative information is used. Such optimization problems are widely seen in many real applications. One particular class of derivative-free optimization algorithms is trust-region algorithms based on quadratic models given by underdetermined interpolation. Different techniques in updating the quadratic model from iteration to iteration will give different interpolation models. In this paper, we propose a new way to update the quadratic model by minimizing the H2 norm of the difference between neighbouring quadratic models. Motivation for applying the H2 norm is given, and theoretical properties of our new updating technique are also presented. Projection in the sense of H2 norm and interpolation error analysis of our model function are proposed. We obtain the coefficients of the quadratic model function by using the KKT conditions. Numerical results show advantages of our model, and the derivative-free algorithms based on our least H2 norm updating quadratic model functions can solve test problems with fewer function evaluations than algorithms based on least Frobenius norm *** Codes 90C56, 90C30, 65K05, 90C90 Copyright © 2023, The Authors. All rights reserved.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Autonomous Robot Navigation in Unknown Terrains using Generative Adversarial Networks

Autonomous Robot Navigation in Unknown Terrains using Genera...

引用

Soft computing for Security Applications (ICSCSA), International Conference on

作者： P Chitra K Sridar Sudha Govindan Britto Raj S Akshya. J Mani Deepak Choudhry M. Sundarrajan Department of Artificial Intelligence and Data Science St Joseph's Institute of Technology Chennai Department of Computer Science and Engineering Veerammal Engineering College Dindigul Department of Computer Science and Engineering Sona College of Technology Salem Department of Computer Science and Engineering RRASE College Of Engineering Chennai Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai Department of Networking and Communications SRM Institute of Science and Technology Chennai

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

Autonomous Robot Navigation in unknown and dynamic environments is considered one of the grand challenges in robotics. These motions that guide it span from rescue operations to planetary exploration. Classical methods for path planning, including A*, Dijkstra, and RRT, were unable to balance the efficiency and adaptability of motion planning over complex terrain. This may have a powerful solution using Generative Adversarial Networks (GANs) with advanced machine learning techniques to improve the ability of robotic navigation. This study proposes a GAN-based approach for designing an effective self-adaptive path planning and obstacle avoidance system for autonomous robots. Despite performing well in structured environments, traditional techniques normally fail in analysing the unstructured terrains with real-time adjustments and dynamic changes due to the high computational costs and lack of flexibility involved. In this regard, the proposed GAN-based system resolves these issues by rating navigation paths concerning safety and efficiency. Quantitative analysis demonstrates that within a forest, desert, urban, or off-road environment, the computational times by using the developed strategy turn out to be 0.12 seconds, 0.10 seconds, 0.14 seconds, and 0.13 seconds, respectively, behaving much lower than what can be achieved with other algorithms. This approach proves much superior in terms of computational efficiency path smoothness and adaptability under different environmental conditions in applications related to autonomous robot navigation systems.

关键词： Navigation Statistical analysis Machine learning Generative adversarial networks Path planning Real-time systems Generators Safety computational efficiency Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

A Dynamical Variable-separation Method for Parameter-dependent Dynamical Systems

arXiv

引用

arXiv 2025年

作者： Chen, Liang Chen, Yaru Li, Qiuqi Zhou, Tao School of Mathematics Hunan University Changsha410082 China LSEC Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

This paper proposes a dynamical Variable-separation method for solving parameter-dependent dynamical systems. To achieve this, we establish a dynamical low-rank approximation for the solutions of these dynamical systems by successively enriching each term in the reduced basis functions via a greedy algorithm. This enables us to reformulate the problem to two decoupled evolution equations at each enrichment step, of which one is a parameter-independent partial differential equation and the other one is a parameter-dependent ordinary differential equation. These equations are directly derived from the original dynamical system and the previously separate representation terms. Moreover, the computational process of the proposed method can be split into an offline stage, in which the reduced basis functions are constructed, and an online stage, in which the efficient low-rank representation of the solution is employed. The proposed dynamical Variable-separation method is capable of offering reduced computational complexity and enhanced efficiency compared to many existing low-rank separation techniques. Finally, we present various numerical results for linear/nonlinear parameter-dependent dynamical systems to demonstrate the effectiveness of the proposed *** Codes 35R60, 37M99, 65P99 Copyright © 2025, The Authors. All rights reserved.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Materials Modeling at Quantum Accuracy: Ab Initio Simulations of Quasicrystals and Interacting Extended Defects in Metallic Alloys 23

Large-Scale Materials Modeling at Quantum Accuracy: Ab Initi...

引用

2023 International Conference for High Performance computing, Networking, Storage and Analysis, SC 2023

作者： Das, Sambit Kanungo, Bikash Subramanian, Vishal Panigrahi, Gourab Motamarri, Phani Rogers, David Zimmerman, Paul Gavini, Vikram Department of Mechanical Engineering University of Michigan Ann Arbor United States Department of Materials Science & Engineering University of Michigan Ann Arbor United States Department of Computational and Data Sciences Indian Institute of Science Bangalore India Scientific Computing Group Oak Ridge National Laboratory Oak Ridge United States Department of Chemistry University of Michigan Ann Arbor United States Department of Materials Science & Engineering University of Michigan Ann Arbor United States

ISBN: (纸本)9798400701092

Ab initio electronic-structure has remained dichotomous between achievable accuracy and length-scale. Quantum many-body (QMB) methods realize quantum accuracy but fail to scale. Density functional theory (DFT) scales favorably but remains far from quantum accuracy. We present a framework that breaks this dichotomy by use of three interconnected modules: (i) invDFT: a methodological advance in inverse DFT linking QMB methods to DFT;(ii) MLXC: a machine-learned density functional trained with invDFT data, commensurate with quantum accuracy;(iii) DFT-FE-MLXC: an adaptive higher-order spectral finite-element (FE) based DFT implementation that integrates MLXC with efficient solver strategies and HPC innovations in FE-specific dense linear algebra, mixed-precision algorithms, and asynchronous compute-communication. We demonstrate a paradigm shift in DFT that not only provides an accuracy commensurate with QMB methods in ground-state energies, but also attains an unprecedented performance of 659.7 PFLOPS (43.1% peak FP64 performance) on 619,124 electrons using 8,000 GPU nodes of Frontier supercomputer. © 2023 ACM.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Detection and Cancellation of Multiplicative FDI Attack on Bilateral Encrypted Control System in Variable Periodic Motion

Detection and Cancellation of Multiplicative FDI Attack on B...

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Kosha, Katsumasa Miyazaki, Tetsuro Teranishi, Kaoru Kogiso, Kiminao Kawashima, Kenji The University of Tokyo Department of Information Physics and Computing 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan The University of Texas at Austin Oden Institute for Computational Engineering and Sciences AustinTX United States Japan Society for the Promotion of Science Tokyo Japan The University of Electro-Communications Department of Mechanical and Intelligent Systems Engineering 1-5-1 ChofugaokaChofu-shi Tokyo182-8585 Japan

ISBN: (纸本)9798331531614

Teleoperation of remote assist robots has recently advanced owing to the development of communication technology. However, anonymous malicious attacks may intercept or falsify the network control system. Therefore, it is necessary to improve the security against cyber-attacks. As a countermeasure, an encrypted control method has been applied to prevent intercepting and detect the falsification of control parameters, as well as control signals by performing control operations with encrypted signals and parameters. Furthermore, we have proposed the algorithm to detect and restore the attack exploiting a vulnerability of encryption, which falsifies the plaintext by multiplying a constant factor. However, the algorithm is only effective for periodic motions with a fixed operating frequency and amplitude. If the frequency or amplitude of the motion is smaller than those of the base motion, the algorithm cannot detect the attack. To solve the problem, we propose an improved algorithm to detect and restore the attack in periodic motion with variable operating frequency and amplitude. In the proposed method, the operating frequency and amplitude are obtained through the position frequency analysis. They contribute to update the base energy, which is the average energy of corresponding periodic motion. We verified the proposed method for the bilateral control system using ElGamal encryption and experimentally confirmed its effectiveness against the FDI attack in various periodic motion. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diabetic Retinopathy Diagnosis with Inception v4: A Deep Learning Approach

Enhancing Diabetic Retinopathy Diagnosis with Inception v4: ...

引用

International Conference on Inventive Research in computing Applications (ICIRCA)

作者： R. Athilakshmi R. Jansi Roshan Upadhyay Department of Computational Intelligence Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Electronics and Communication Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Computational Intelligence Faculty of Engineering and Technology School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu India

An automated system for the classification of Diabetic Retinopathy (DR) is introduced in this study. DR is a prominent cause of blindness globally, primarily impacting individuals aged 20 to 65. The proposed system can be an essential tool in the sustainable healthcare industry, providing timely and accurate diagnosis and treatment to patients with DR. Current manual screening by ophthalmologists can be time-consuming. Accurate categorization of DR is crucial to provide appropriate care and reduce the likelihood of permanent blindness. The use of big data and deep learning models in DR detection has the potential to revolutionize screening and diagnosis, leading to improved patient outcomes and reduced healthcare costs. This study compares traditional and CNN models, including Decision Trees, Random Forest, KNN, SVM, and Inception V4, to identify the best model for classifying retinal images into five stages of DR severity: No DR, Mild, Moderate, Severe, and Proliferative DR. Among the models tested, Inceptionv4 demonstrated the highest accuracy of 92.83% in classifying DR data. These findings demonstrate the potential of an automated system to improve DR diagnosis and management.

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：