检索结果-内蒙古大学图书馆

International Conference on science Technology Engineering and Management (ICONSTEM)

作者： P. Sathyaraj S. Arulkumar A. Ajina Kedir Beshir L. Umasankar A.N. Arularasan Department of Electronics and Communication Engineering RMK College of Engineering and Technology Puduvoyal Tamil Nadu India Department of Electrical and Computer Engineering Wachemo University Ethiopia Department of Artificial Intelligence and Machine Learning M S Ramaiah Institute of Technology Bangalore India Department of Electrical and Electronics Engineering S.A. Engineering College Tiruvallur Tamil Nadu India Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

Rapid electronic device development requires more complicated and densely packed PCB designs. These systems need properly placed and connected electrical components for best performance and reliability. Complexity and time restrictions are rendering manual methods ineffective. Therefore, AI-based PCB insertion and routing automation methods have been developed. This research suggests using AI to optimize PCB component arrangement and routing. The system uses machine learning and optimization to improve design efficiency. The AI system creates layouts that match performance requirements, decrease signal interference, and meet manufacturing limits using previous design data and user preferences. A learning module that updates its knowledge base, an algorithm that chooses between design objectives, and real-time user input are examples. Signal integrity, thermal issues, and manufacturability are considered while modifying design requirements. Evaluation of the suggested methodology shows considerable gains in design efficiency, time-to-market, and electronic system performance. This research improves AI-automated PCB design, enabling more complex and effective electrical systems. AI in PCB design will revolutionize the industry by solving complicated design problems and speeding up the development of cutting-edge electronics.

关键词： machine learning algorithms System performance machine learning Routing Rendering (computer graphics) Real-time systems Reliability

来源：评论

学校读者我要写书评

暂无评论

Uncertainty quantification for wide-bin unfolding: one-at-a-time strict bounds and prior-optimized confidence intervals

arXiv

引用

arXiv 2021年

作者： Stanley, Michael Patil, Pratik Kuusela, Mikael Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Department of Statistics and Data Science NSF AI Planning Institute for Data-Driven Discovery in Physics Carnegie Mellon University PittsburghPA15213 United States

Unfolding is an ill-posed inverse problem in particle physics aiming to infer a true particle-level spectrum from smeared detector-level data. For computational and practical reasons, these spaces are typically discretized using histograms, and the smearing is modeled through a response matrix corresponding to a discretized smearing kernel of the particle detector. This response matrix depends on the unknown shape of the true spectrum, leading to a fundamental systematic uncertainty in the unfolding problem. To handle the ill-posed nature of the problem, common approaches regularize the problem either directly via methods such as Tikhonov regularization, or implicitly by using wide-bins in the true space that match the resolution of the detector. Unfortunately, both of these methods lead to a non-trivial bias in the unfolded estimator, thereby hampering frequentist coverage guarantees for confidence intervals constructed from these methods. We propose two new approaches to addressing the bias in the wide-bin setting through methods called One-at-a-time Strict Bounds (OSB) and Prior-Optimized (PO) intervals. The OSB intervals are a bin-wise modification of an existing guaranteed-coverage procedure, while the PO intervals are based on a decision-theoretic view of the problem. Importantly, both approaches provide well-calibrated frequentist confidence intervals even in constrained and rank-deficient settings. These methods are built upon a more general answer to the wide-bin bias problem, involving unfolding with fine bins first, followed by constructing confidence intervals for linear functionals of the fine-bin counts. We test and compare these methods to other available methodologies in a wide-bin deconvolution example and a realistic particle physics simulation of unfolding a steeply falling particle *** Codes 15A29, 62F30, 62C05, 90C90. © 2021, CC BY.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

The Alchemical Integral Transform revisited

arXiv

引用

arXiv 2023年

作者： Krug, Simon León von Lilienfeld, O. Anatole Machine Learning Group Technische Universität Berlin Berlin10587 Germany Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany Chemical Physics Theory Group Department of Chemistry University of Toronto St. George Campus TorontoON Canada Department of Materials Science and Engineering University of Toronto St. George Campus TorontoON Canada Vector Institute for Artificial Intelligence TorontoON Canada Department of Physics University of Toronto St. George Campus TorontoON Canada Acceleration Consortium University of Toronto TorontoON Canada

We recently introduced the Alchemical Integral Transform (AIT) enabling the prediction of energy differences, and guessed an Ansatz to parametrize space r in some alchemical change λ. Here, we present a rigorous derivation of AIT’s kernel K and discuss the parametrization r(λ) in n dimensions, i.e. necessary conditions, mathematical freedoms and additional constraints when obtaining it. Analytical expressions for changes in energy spectra and densities are given for a number of systems. Examples include homogeneous potentials like the quantum harmonic oscillator, Hydrogen-like atom, and Dirac well, both for one- and multiparticle cases, and a multiparticle system beyond coordinate scaling for harmonic potentials. © 2023, CC BY.

关键词： Choquet integral

来源：评论

学校读者我要写书评

暂无评论

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

arXiv

引用

arXiv 2025年

作者： Pach, Mateusz Karthik, Shyamgopal Bouniot, Quentin Belongie, Serge Akata, Zeynep Technical University of Munich Germany Helmholtz Munich Germany Munich Center of Machine Learning Germany Munich Data Science Institute Germany University of Tübingen Germany University of Copenhagen Denmark

Sparse Autoencoders (SAEs) have recently been shown to enhance interpretability and steerability in Large Language Models (LLMs). In this work, we extend the application of SAEs to Vision-Language Models (VLMs), such as CLIP, and introduce a comprehensive framework for evaluating monosemanticity in vision representations. Our experimental results reveal that SAEs trained on VLMs significantly enhance the monosemanticity of individual neurons while also exhibiting hierarchical representations that align well with expert-defined structures (e.g., iNaturalist taxonomy). Most notably, we demonstrate that applying SAEs to intervene on a CLIP vision encoder, directly steer output from multimodal LLMs (e.g., LLaVA) without any modifications to the underlying model. These findings emphasize the practicality and efficacy of SAEs as an unsupervised approach for enhancing both the interpretability and control of VLMs. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-convex distributionally robust optimization: non-asymptotic analysis 21

Non-convex distributionally robust optimization: non-asympto...

引用

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

作者： Jikai Jin Bohang Zhang Haiyang Wang Liwei Wang School of Mathematical Sciences Peking University Key Laboratory of Machine Perception MOE School of EECS Peking University Center of Data Science Peking University Key Laboratory of Machine Perception MOE School of EECS Peking University and Center of Data Science Peking University and Institute for Artificial Intelligence Peking Unviersity

ISBN: (纸本)9781713845393

Distributionally robust optimization (DRO) is a widely-used approach to learn models that are robust against distribution shift. Compared with the standard optimization setting, the objective function in DRO is more difficult to optimize, and most of the existing theoretical results make strong assumptions on the loss function. In this work we bridge the gap by studying DRO algorithms for general smooth non-convex losses. By carefully exploiting the specific form of the DRO objective, we are able to provide non-asymptotic convergence guarantees even though the objective function is possibly non-convex, non-smooth and has unbounded gradient noise. In particular, we prove that a special algorithm called the mini-batch normalized gradient descent with momentum, can find an ∈-first-order stationary point within O(∈-4) gradient complexity. We also discuss the conditional value-at-risk (CVaR) setting, where we propose a penalized DRO objective based on a smoothed version of the CVaR that allows us to obtain a similar convergence guarantee. We finally verify our theoretical results in a number of tasks and find that the proposed algorithm can consistently achieve prominent acceleration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ab Initio Generalized Langevin Equation

arXiv

引用

arXiv 2022年

作者： Xie, Pinchen Car, Roberto Weinan, E. Program in Applied and Computational Mathematics Princeton University PrincetonNJ08544 United States Department of Chemistry Department of Physics Program in Applied and Computational Mathematics Princeton Institute for the Science and Technology of Materials Princeton University PrincetonNJ08544 United States AI for Science Institute Beijing China Center for Machine Learning Research School of Mathematical Sciences Peking University Beijing China

We introduce a machine learning-based approach called ab initio generalized Langevin equation (AIGLE) to model the dynamics of slow collective variables in materials and molecules. In this scheme, the parameters are learned from atomistic simulations based on ab initio quantum mechanical models. Force field, memory kernel, and noise generator are constructed in the context of the Mori-Zwanzig formalism, under the constraint of the fluctuation-dissipation theorem. Combined with deep potential molecular dynamics and electronic density functional theory, this approach opens the way to multi-scale modeling in a variety of situations. Here, we demonstrate this capability with a study of two mesoscale processes in crystalline lead titanate, namely the field-driven dynamics of a planar ferroelectric domain wall, and the dynamics of an extensive lattice of coarse-grained electric dipoles. In the first case, AIGLE extends the reach of ab initio simulations to a regime of noise-driven motions not accessible to molecular dynamics. In the second case, AIGLE deals with an extensive set of collective variables by adopting a local approximation for the memory kernel and retaining only short-range noise correlations. The scheme is computationally more efficient than molecular dynamics by several orders of magnitude, and mimics the microscopic dynamics at low frequencies where it reproduces accurately the dominant far-infrared absorption frequency. © 2022, CC BY.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Secure Device on boarding in IoT Networks

Secure Device on boarding in IoT Networks

引用

International Conference on science Technology Engineering and Management (ICONSTEM)

作者： P. Sathyaraj Shankar Nayak Bhukya S. Rukmani Devi Chetan Umadi A. Ajina Rajendiran M Department of Electronics and Communication Engineering RMK College of Engineering and Technology Puduvoyal Tamil Nadu India Department of Computer Science Engineering (Data Science) CMR Technical Campus Hyderabad Telangana India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India Department of Electronics& Telecommunication Engineering Dayananda Sagar College of Engineering Bengaluru Karnataka India Department of Artificial Intelligence and Machine Learning M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering Panimalar Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

The fast spread of Internet of Things (IoT) gadgets has led to unprecedented number of interconnected systems offering many applications and services. Diverse elements in IoT networks increase security vulnerabilities, especially when adding new devices. IoT device onboarding secures device integration, authentication, and network connection authorization. This research shows the hazards and limitations of secure IoT device connections. Research examines onboarding protocols' merits and downsides. Bootstrapping, mutual authentication, and key establishment protect the IoT device-network connection in the proposed architecture. Overcoming scalability and resource constraints makes onboarding several IoT devices straightforward. We also analyze IoT network security with PKI and certificate-based authentication. Safe communication pathways and ongoing observation and system adjustments to address new security issues are discussed in this essay. Researchers test the technology in IoT environments. The framework handles onboarding in this case. The method safeguards onboarding and IoT ecosystem data, research demonstrate. A detailed device onboarding approach increases IoT security talks. The framework fixes onboarding issues and vulnerabilities for secure IoT networks.

关键词： Protocols Scalability Ecosystems Authentication Interconnected systems Network security Mathematics

来源：评论

学校读者我要写书评

暂无评论

End-to-end topographic networks as models of cortical map formation and human visual behaviour: moving beyond convolutions

arXiv

引用

arXiv 2023年

作者： Lu, Zejin Doerig, Adrien Bosch, Victoria Krahmer, Bas Kaiser, Daniel Cichy, Radoslaw M. Kietzmann, Tim C. Machine Learning Institute for Cognitive Science Osnabrück University Osnabrück Germany Neural Computation Group Mathematical Institute Justus-Liebig-Universität Gießen Gießen Germany Center for Mind Brain and Behavior Philipps-Universität Marburg and Justus-Liebig-Universität Gießen Marburg Germany Neural Dynamics of Visual Cognition Group Department of Education and Psychology Freie Universität Berlin Berlin Germany

Computational models are an essential tool for understanding the origin and functions of the topographic organisation of the primate visual system. Yet, vision is most commonly modelled by convolutional neural networks that ignore topography by learning identical features across space. Here, we overcome this limitation by developing All-Topographic Neural Networks (All-TNNs). Trained on visual input, several features of primate topography emerge in All-TNNs: smooth orientation maps and cortical magnification in their first layer, and category-selective areas in their final layer. In addition, we introduce a novel dataset of human spatial biases in object recognition, which enables us to directly link models to behaviour. We demonstrate that All-TNNs significantly better align with human behaviour than previous state-of-the-art convolutional models due to their topographic nature. All-TNNs thereby mark an important step forward in understanding the spatial organisation of the visual brain and how it mediates visual behaviour. © 2023, CC BY.

关键词： Topography

来源：评论

学校读者我要写书评

暂无评论

Overview of the Tenth Dialog System Technology Challenge: DSTC10

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

Unleashing WSN Potential: Bowerbird Optimized Energy-Conscious Multipath Clustering with Causal Dilated Cosine for Enhanced Load Balancing

Unleashing WSN Potential: Bowerbird Optimized Energy-Conscio...

引用

Sentiment Analysis and Deep learning (ICSADL), International Conference on

作者： Rakesh Kumar Joon Anitha R Saravana Selvan P. S. Latha Mageshwari S. Gayathri Priya K. Malathi Department of Electronics and Communication Engineering Ganga Institute of Technology and Management Kablana Haryana India Department of Artificial Intelligence and Data Science S.A. Engineering College Chennai Tamil Nadu India School of Professional Engineering Manukau Institute of Technology Auckland New Zealand Department of Science & Humanities (Physics) R. M. K. Engineering College Kavaraipettai Tamil Nadu India Department of Electronics and Communication Engineering R.M.D. Engineering College Kavaraipettai Tamil Nadu India Department of Artificial Intelligence and Machine Learning Saveetha Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Wireless Sensor Networks (WSNs) are essential in the collection of real time data across different fields, including environmental monitoring and process control. However, due to the bounded amount of energy in sensor nodes, network lifetime becomes an issue, which hinders performance and reliability. Thus, optimization of WSN performance in an attempt to minimize energy consumption is essential for reliable data transmission. In conventional routing and clustering models, network load distribution is not achieved adequately, resulting in a more significant loading of nodes and faster exhaustion of energy. To solve these problems, it is necessary to carefully design load distribution and path finding algorithms to support long-term WSN operation. The objective of this research is to design a framework-Ski-CDiCo-BO-that integrates Skill Optimization for clustering, and ensuring an energy-efficient paths while reducing redundant transmissions on nodes and conserving node energies, and uses the Causal Dilated Cosine Architecture for sophisticated load balancing, and Bowerbird Optimization for improving the parameterization of neural networks. Analysis reveals that the presented Ski-CDiCo-BO framework provides improved performance of various parameters including data delivery success rate of above 99.8% and network lifetime gain by up to 99.5%. Also, load distribution accuracy remains above 99.3%, which indicates that the framework is capable of avoiding node overload and end-to-end delay improved upon by 99.6%, indicating that the solution maintains high parameters even in dynamically changing conditions. In conclusion, Ski-CDiCo-BO maximizes WSN efficiency by implementing cutting-edge clustering, load balancing, and optimization techniques, setting new standards for energy-conscious and reliable sensor network performance across diverse applications.

关键词： Wireless sensor networks Energy consumption Scalability Heuristic algorithms Load management Routing Energy efficiency Reliability Environmental monitoring Optimization

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：