检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Adams, Steven Patanè, Andrea Lahijanian, Morteza Laurenti, Luca Delft Center for Systems and Control Technical Universiy of Delft Delft2628 CD Netherlands School of Computer Science and Statistics Trinity College Dublin Dublin 2 Ireland Department of Aerospace Engineering Sciences and Computer Science University of Colorado Boulder BoulderCO80303 United States

Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this equivalence is commonly employed to analyze neural networks and has led to various breakthroughs over the years. However, neural networks and Gaussian processes are equivalent only in the limit;in the finite case there are currently no methods available to approximate a trained neural network with a Gaussian model with bounds on the approximation error. In this work, we present an algorithmic framework to approximate a neural network of finite width and depth, and with not necessarily i.i.d. parameters, with a mixture of Gaussian processes with error bounds on the approximation error. In particular, we consider the Wasserstein distance to quantify the closeness between probabilistic models and, by relying on tools from optimal transport and Gaussian processes, we iteratively approximate the output distribution of each layer of the neural network as a mixture of Gaussian processes. Crucially, for any NN and ǫ > 0 our approach is able to return a mixture of Gaussian processes that is ǫ-close to the NN at a finite set of input points. Furthermore, we rely on the differentiability of the resulting error bound to show how our approach can be employed to tune the parameters of a NN to mimic the functional behavior of a given Gaussian process, e.g., for prior selection in the context of Bayesian inference. We empirically investigate the effectiveness of our results on both regression and classification problems with various neural network architectures. Our experiments highlight how our results can represent an important step towards understanding neural network predictions and formally quantifying their uncertainty. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMABILITY REVEALS THE INTERPLAY OF DYNAMICS ACROSS DIFFERENT NETWORK ORDERS

arXiv

引用

arXiv 2025年

作者： Xie, Ming He, Shibo Li, Aming Zhang, Zike Sun, Youxian Chen, Jiming Department of Control Science and Engineering Zhejiang University Hangzhou310027 China Center for Systems and Control College of Engineering Peking University Beijing100871 China College of Media and International Culture Zhejiang University Hangzhou310058 China

Recent studies have investigated various dynamic processes characterizing collective behaviors in real-world systems. However, these dynamics have been studied individually in specific contexts. In this article, we present a holistic analysis framework that bridges the interplays between dynamics across networks of different orders, demonstrating that these processes are not independent but can undergo systematic transformations. Focusing on contagion dynamics, we identify and quantify dynamical and structural factors that explains the interplay between dynamics on higher-order and pairwise networks, uncovering a universal model for system instability governed by these factors. Furthermore, we validate the findings from contagion dynamics to opinion dynamics, highlighting its broader applicability across diverse dynamical processes. Our findings reveal the intrinsic coupling between diverse dynamical processes, providing fresh insights into the distinct role of complex dynamics governed by higher-order interactions. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Clustering Based Transmission Protocol for Wireless Body Area Networks

引用

computers, Materials & Continua 2021年第11期69卷 2459-2473页

作者： Neelam Sharma Harshita Chadha Karan Singh B.M.Singh Nitish Pathak Research Scholar Computer Science and EngineeringUttarakhand Technical University(UTU)DehradunIndia Computer Science and Engineering Maharaja Agrasen Institute of TechnologyNew DelhiIndia School of Computer&Systems Sciences Jawaharlal Nehru University(JNU)DelhiIndia College of Engineering Roorkee UTUDehradunIndia Department of Information Technology KIET Group of InstitutionsGhaziabadIndia

Wireless sensor networks are a collection of intelligent sensor devices that are connected to one another and have the capability to exchange information packets amongst *** recent years,this field of research has become increasingly popular due to the host of useful applications it can potentially serve.A deep analysis of the concepts associated with this domain reveals that the two main problems that are to be tackled here are throughput enhancement and network security *** present article takes on one of these two issues namely the throughput *** the purpose of improving network productivity,a hybrid clustering based packet propagation protocol has been *** protocol makes use of not only clustering mechanisms of machine learning but also utilizes the traditional forwarding function approach to arrive at an optimum *** result of the simulation is a novel transmission protocol which significantly enhances network productivity and increases throughput value.

关键词： Forwarding function wireless sensor networks WSNs WBANs energy characteristics clustering hybrid mechanism dissipated energy network stability

来源：评论

学校读者我要写书评

暂无评论

Design of an RF-CMOS Switched-Capacitor Power Amplifier for NB-IoT RF Transceivers

Design of an RF-CMOS Switched-Capacitor Power Amplifier for ...

引用

International Young Engineers Forum (YEF-ECE)

作者： Ana Isabel Santos João Pedro Oliveira Department of Electrical and Computer Engineering NOVA School of Science and Technology Caparica Portugal Department of Electrical and Computer Engineering Centre of Technology and Systems CTS – UNINOVA Caparica Portugal

The paper presents the implementation of a Switched Capacitor Power Amplifier (SCPA) to be integrated into a Narrowband Internet of Things (NB-IoT) Transceiver. The SCPA is designed to operate at a frequency of 0.9GHz and aiming the maximum output power allowed by the standard of 23dBm. All the blocks within the SCPA were developed using RF components of a standard 130nm CMOS process, with a 1.2V/2.4V supply voltage. Results show that the SCPA is able to produce a maximum output power of 15.61dBm with a maximum Power-Added Efficiency (PAE) of 26.52% and a Total Harmonic Distortion (THD) of 0.68%. The measured HD2 and HD3 are -70.23dBc and -43.41dBc, respectively. Additional Process, Voltage and Temperature (PVT) corners and Monte Carlo simulations indicate the SCPA operates properly when subject to different conditions and mismatches. Besides the SCPA, a 16 QAM modulation stage is designed in VerilogA in order to evaluate the performance of the RF PA when a sequence of symbols is transmitted.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning of Nash Equilibria in Risk-Averse Games

arXiv

引用

arXiv 2024年

作者： Wang, Zifan Shen, Yi Zavlanos, Michael M. Johansson, Karl H. Division of Decision and Control Systems School of Electrical Enginnering and Computer Science KTH Royal Institute of Technology Digital Futures StockholmSE-10044 Sweden The Department of Mechanical Engineering and Materials Science Duke University DurhamNC United States

This paper considers risk-averse learning in convex games involving multiple agents that aim to minimize their individual risk of incurring significantly high costs. Specifically, the agents adopt the conditional value at risk (CVaR) as a risk measure with possibly different risk levels. To solve this problem, we propose a first-order risk-averse leaning algorithm, in which the CVaR gradient estimate depends on an estimate of the Value at Risk (VaR) value combined with the gradient of the stochastic cost function. Although estimation of the CVaR gradients using finitely many samples is generally biased, we show that the accumulated error of the CVaR gradient estimates is bounded with high probability. Moreover, assuming that the risk-averse game is strongly monotone, we show that the proposed algorithm converges to the risk-averse Nash equilibrium. We present numerical experiments on a Cournot game example to illustrate the performance of the proposed method. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Closer through commonality: Enhancing hypergraph contrastive learning with shared groups

arXiv

引用

arXiv 2025年

作者： Roh, Daeyoung Han, Donghee Kim, Daehee Han, Keejun Yi, Mun Graduate School of Data Science KAIST Korea Republic of School of Computer Engineering Hansung University Korea Republic of Department of Industrial and Systems Engineering KAIST Korea Republic of

Hypergraphs provide a superior modeling framework for representing complex multidimensional relationships in the context of real-world interactions that often occur in groups, overcoming the limitations of traditional homogeneous graphs. However, there have been few studies on hypergraph-based contrastive learning, and existing graph-based contrastive learning methods have not been able to fully exploit the high-order correlation information in hypergraphs. Here, we propose a Hypergraph Fine-grained contrastive learning (HyFi) method designed to exploit the complex high-dimensional information inherent in hypergraphs. While avoiding traditional graph augmentation methods that corrupt the hypergraph topology, the proposed method provides a simple and efficient learning augmentation function by adding noise to node features. Furthermore, we expands beyond the traditional dichotomous relationship between positive and negative samples in contrastive learning by introducing a new relationship of weak positives. It demonstrates the importance of fine-graining positive samples in contrastive learning. Therefore, HyFi is able to produce high-quality embeddings, and outperforms both supervised and unsupervised baselines in average rank on node classification across 10 datasets. Our approach effectively exploits high-dimensional hypergraph information, shows significant improvement over existing graph-based contrastive learning methods, and is efficient in terms of training speed and GPU memory cost. The source code is available at https://***/Noverse0/***. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Improving Air Mobility for Pre-Disaster Planning with Neural Network Accelerated Genetic Algorithm 27

Improving Air Mobility for Pre-Disaster Planning with Neural...

引用

27th IEEE International Conference on Intelligent Transportation systems, ITSC 2024

作者： Acharya, Kamal Velasquez, Alvaro Liu, Yongxin Liu, Dahai Sun, Liang Song, Houbing Herbert Department of Information Systems Baltimore County BaltimoreMD21250 United States University of Colorado Department of Computer Science BoulderCO80309 United States Embry-Riddle Aeronautical University Mathematics Department and College of Aviation Daytona BeachFL32114 United States Baylor University Department of Mechanical Engineering WacoTX76798 United States

ISBN: (纸本)9798331505929

Weather disaster related emergency operations pose a great challenge to air mobility in both aircraft and airport operations, especially when the impact is gradually approaching. We propose an optimized framework for adjusting airport operational schedules for such pre-disaster scenarios. We first, aggregate operational data from multiple airports and then determine the optimal count of evacuation flights to maximize the impacted airport's outgoing capacity without impeding regular air traffic. We then propose a novel Neural Network (NN) accelerated Genetic Algorithm (GA) for evacu-ation planning. Our experiments show that integration yielded comparable results but with smaller computational overhead. We find that the utilization of a NN enhances the efficiency of a GA, facilitating more rapid convergence even when operating with a reduced population size. This effectiveness persists even when the model is trained on data from airports different from those under test. Data and code available at github11Github: https://***/lotussavy/ITSC-2024. © 2024 IEEE.

关键词： air mobility air traffic management evacuation genetic algorithm neural network planning

来源：评论

学校读者我要写书评

暂无评论

Leveraging LLMs for Multimodal Medical Time Series Analysis 9

Leveraging LLMs for Multimodal Medical Time Series Analysis

引用

9th Machine Learning for Healthcare Conference, MLHC 2024

作者： Chan, Nimeesha Parker, Felix Bennett, William Wu, Tianyi Jia, Mung Yao Fackler, James Ghobadi, Kimia Department of Civil and Systems Engineering Johns Hopkins University BaltimoreMD United States Department of Anesthesiology and Critical Care Medicine Johns Hopkins University BaltimoreMD United States Department of Applied Mathematics and Statistics Johns Hopkins University BaltimoreMD United States Department of Computer Science Johns Hopkins University BaltimoreMD United States

The complexity and heterogeneity of data in many real-world applications pose significant challenges for traditional machine learning and signal processing techniques. For instance, in medicine, effective analysis of diverse physiological signals is crucial for patient monitoring and clinical decision-making and yet highly challenging. We introduce MedTsLLM, a general multimodal large language model (LLM) framework that effectively integrates time series data and rich contextual information in the form of text to analyze physiological signals, performing three tasks with clinical relevance: semantic segmentation, boundary detection, and anomaly detection in time series. These critical tasks enable deeper analysis of physiological signals and can provide actionable insights for clinicians. We utilize a reprogramming layer to align embeddings of time series patches with a pretrained LLM’s embedding space and make effective use of raw time series, in conjunction with textual context. Given the multivariate nature of medical datasets, we develop methods to handle multiple covariates. We additionally tailor the text prompt to include patient-specific information. Our model outperforms state-of-the-art baselines, including deep learning models, other LLMs, and clinical methods across multiple medical domains, specifically electrocardiograms and respiratory waveforms. MedTsLLM presents a promising step towards harnessing the power of LLMs for medical time series analysis that can elevate data-driven tools for clinicians and improve patient outcomes. © 2024 Authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Closing the Intent-to-Reality Gap via Fulfillment Priority Logic

arXiv

引用

arXiv 2025年

作者： El Mabsout, Bassel Abdelgawad, Abdelrahman Mancuso, Renato Department of Computer Science Boston University BostonMA United States Systems Engineering Division Boston University BostonMA United States

Practitioners designing reinforcement learning policies face a fundamental challenge: translating intended behavioral objectives into representative reward functions. This challenge stems from behavioral intent requiring simultaneous achievement of multiple competing objectives, typically addressed through labor-intensive linear reward composition that yields brittle results. Consider the ubiquitous robotics scenario where performance maximization directly conflicts with energy conservation. Such competitive dynamics are resistant to simple linear reward combinations. In this paper, we present the concept of objective fulfillment upon which we build Fulfillment Priority Logic (FPL). FPL allows practioners to define logical formula representing their intentions and priorities within multiobjective reinforcement learning. Our novel Balanced Policy Gradient algorithm leverages FPL specifications to achieve up to 500% better sample efficiency compared to Soft Actor Critic. Notably, this work constitutes the first implementation of nonlinear utility scalarization design, specifically for continuous control problems. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Structure-Aware Argument Encoder for Literature Discourse Analysis 29

A Structure-Aware Argument Encoder for Literature Discourse ...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Li, Yinzi Chen, Wei Wei, Zhongyu Huang, Yujun Wang, Chujun Wang, Siyuan Zhang, Qi Huang, Xuanjing Wu, Libo School of Data Science Fudan University China Research Institute of Intelligent Complex Systems Fudan University China Department of Environmental Science and Engineering Fudan University China School of Computer Science Fudan University China

Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context. In this paper, we propose to separate tokens into two groups, namely framing tokens and topic ones, to capture structural information of arguments. In addition, we consider high-level structure by incorporating paragraph-level position information. A novel structure-aware argument encoder is proposed for literature discourse analysis. Experimental results on both a self-constructed corpus and a public corpus show the effectiveness of our model. Resources are available at https://***/lemuria-wchen/SAE. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Signal encoding

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：