检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Läufer, Konstantin Mertin, Gunda Thiruvathukal, George K. Software and Systems Laboratory Department of Computer Science Loyola University Chicago United States Institute for Software Engineering and Programming Languages University of Lübeck Germany

Background: In this Innovative Practice Work in Progress, we present our initial efforts to integrate formal methods, with a focus on model-checking specifications written in Temporal Logic of Actions (TLA+), into computer science education, targeting undergraduate juniors/seniors and graduate students. Many safety-critical systems and services crucially depend on correct and reliable behavior. Formal methods can play a key role in ensuring correct and safe system behavior, yet remain underutilized in educational and industry contexts. Aims: We aim to (1) qualitatively assess the state of formal methods in computer science programs, (2) construct level-appropriate examples that could be included midway into one’s undergraduate studies, (3) demonstrate how to address successive "failures" through progressively stringent safety and liveness requirements, and (4) establish an ongoing framework for assessing interest and relevance among students. Methods: We detail our pedagogical strategy for embedding TLA+ into an intermediate course on formal methods at our institution. After starting with a refresher on mathematical logic, students specify the rules of simple puzzles in TLA+ and use its included model checker (known as TLC) to find a solution. We gradually escalate to more complex, dynamic, event-driven systems, such as the control logic of a microwave oven, where students will study safety and liveness requirements. We subsequently discuss explicit concurrency, along with thread safety and deadlock avoidance, by modeling bounded counters and buffers. Results: Our initial findings suggest that through careful curricular design and choice of examples and tools, it is possible to inspire and cultivate a new generation of software engineers proficient in formal methods. Conclusions: Our initial efforts suggest that 84% of our students had a positive experience in our formal methods course. Our future plans include a longitudinal analysis within our own institution and

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Deep learning for automatically predicting early haematoma expansion in Chinese patients

引用

Stroke & Vascular Neurology 2021年第4期6卷 610-614,I0067-I0072页

作者： Jia-wei Zhong Yu-jia Jin Zai-jun Song Bo Lin Xiao-hui Lu Fang Chen Lu-sha Tong Department of Neurology Zhejiang University School of Medicine Second Affiliated HospitalHangzhouChina College of Computer Science and Technology Zhejiang UniversityHangzhouChina State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University School of Mechanical EngineeringHangzhouChina Department of Computer Science and Engineering Nanjing University of Aeronautics and AstronauticsNanjingChina

Background and purpose Early haematoma expansion is determinative in predicting outcome of intracerebral haemorrhage(ICH)*** aims of this study are to develop a novel prediction model for haematoma expansion by applying deep learning model and validate its prediction *** Data of this study were obtained from a prospectively enrolled cohort of patients with primary supratentorial ICH from our *** developed a deep learning model to predict haematoma expansion and compared its performance with conventional non-contrast CT(NCCT)*** evaluate the predictability of this model,it was also compared with a logistic regression model based on haematoma volume or the BAT *** A total of 266 patients were finally included for analysis,and 74(27.8%)of them experienced early haematoma *** deep learning model exhibited highest C statistic as 0.80,compared with 0.64,0.65,0.51,0.58 and 0.55 for hypodensities,black hole sign,blend sign,fluid level and irregular shape,*** the C statistics for swirl sign(0.70;p=0.211)and heterogenous density(0.70;p=0.141)were not significantly higher than that of the deep learning ***,the predictive value for the deep learning model was significantly superior to that of the logistic model of haematoma volume(0.62;p=0.042)and the BAT score(0.65;p=0.042).Conclusions Compared with the conventional NCCT markers and BAT predictive model,the deep learning algorithm showed superiority for predicting early haematoma expansion in ICH patients.

关键词： patients expansion predicting

来源：评论

学校读者我要写书评

暂无评论

On the properties of kullback-leibler divergence between multivariate Gaussian distributions 23

On the properties of kullback-leibler divergence between mul...

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Yufeng Zhang Jialu Pan Kenli Li Wanwei Liu Zhenbang Chen Xinwang Liu Ji Wang College of Computer Science and Electronic Engineering Hunan University Changsha China College of Computer Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China College of Computer State Key Laboratory for High Performance Computing Key laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China

Kullback-Leibler (KL) divergence is one of the most important measures to calculate the difference between probability distributions. In this paper, we theoretically study several properties of KL divergence between multivariate Gaussian distributions. Firstly, for any two n-dimensional Gaussian distributions Ɲ1 and Ɲ2, we prove that when KL(Ɲ2‖Ɲ1) ≤ ε (ε > 0) the supremum of KL (Ɲ1‖Ɲ2) is (1/2) ((-W0 (-e-(1+2ε)))-1 + log(-W0 (-e-(1+2ε))) - 1), where W0 is the principal branch of Lambert W function. For small ε, the supremum is ε + 2ε1.5 + O (ε2). This quantifies the approximate symmetry of small KL divergence between Gaussian distributions. We further derive the infimum of KL(Ɲ1‖Ɲ2) when KL(Ɲ2‖Ɲ1) ≥ M (M > 0). We give the conditions when the supremum and infimum can be attained. Secondly, for any three n-dimensional Gaussian distributions Ɲ1, Ɲ2, and Ɲ3, we theoretically show that an upper bound of KL (Ɲ1‖Ɲ3) is 3ε1 + 3ε2 + 2√ε1ε2 + o(ε1)+ o(ε2) when KL (Ɲ1‖Ɲ2) ≤ ε1 and KL(Ɲ2‖Ɲ3) ≤ ε2 (ε1, ε2 ≥ 0). This reveals that KL divergence between Gaussian distributions follows a relaxed triangle inequality. Note that, all these bounds in the theorems presented in this work are independent of the dimension n. Finally, we discuss several applications of our theories in deep learning, reinforcement learning, and sample complexity research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Training Graph Neural Networks on Growing Stochastic Graphs

Training Graph Neural Networks on Growing Stochastic Graphs

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Juan Cerviño Luana Ruiz Alejandro Ribeiro Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia USA Computer Science & Artificial Intelligence Laboratory MIT Cambridge USA

Graph Neural Networks (GNNs) rely on graph convolutions to exploit meaningful patterns in networked data. Based on matrix multiplications, convolutions incur in high computational costs leading to scalability limitations in practice. To overcome these limitations, proposed methods rely on training GNNs in smaller number of nodes, and then transferring the GNN to larger graphs. Even though these methods are able to bound the difference between the output of the GNN with different number of nodes, they do not provide guarantees against the optimal GNN on the very large graph. In this paper, we propose to learn GNNs on very large graphs by leveraging the limit object of a sequence of growing graphs, the graphon. We propose to grow the size of the graph as we train, and we show that our proposed methodology – learning by transference – converges to a neighborhood of a first order stationary point on the graphon data. A numerical experiment validates our proposed approach.

关键词： Training Convolution Scalability Signal processing algorithms Graph neural networks Acoustics Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Efficient displacement convex optimization with particle gradient descent

arXiv

引用

arXiv 2023年

作者： Daneshmand, Hadi Lee, Jason D. Jin, Chi Laboratory for Information and Decision Systems MIT United States Department of Electrical Engineering and Computer Science Princeton Universit United States

Particle gradient descent, which uses particles to represent a probability measure and performs gradient descent on particles in parallel, is widely used to optimize functions of probability measures. This paper considers particle gradient descent with a finite number of particles and establishes its theoretical guarantees to optimize functions that are displacement convex in measures. Concretely, for Lipschitz displacement convex functions defined on probability over Rd, we prove that O(1/ϵ2) particles and O(d/ϵ4) computations are sufficient to find the ϵ-optimal solutions. We further provide improved complexity bounds for optimizing smooth displacement convex functions. We demonstrate the application of our results for function approximation with specific neural architectures with two-dimensional inputs. © 2023, CC BY-NC-ND.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Understanding Reinforcement Learning Algorithms: The Progress from Basic Q-learning to Proximal Policy Optimization

arXiv

引用

arXiv 2023年

作者： Chadi, Mohamed-Amine Mousannif, Hajar Laboratory of Informatics Systems Engineering Department of Computer Science Faculty of Sciences Semlalia University of Cadi Ayyad Marrakech40000 Morocco

This paper presents a review of the field of reinforcement learning (RL), with a focus on providing a comprehensive overview of the key concepts, techniques, and algorithms for beginners. RL has a unique setting, jargon, and mathematics that can be intimidating for those new to the field or artificial intelligence more broadly. While many papers review RL in the context of specific applications, such as games, healthcare, finance, or robotics, these papers can be difficult for beginners to follow due to the inclusion of non-RL-related work and the use of algorithms customized to those specific applications. To address these challenges, this paper provides a clear and concise overview of the fundamental principles of RL and covers the different types of RL algorithms. For each algorithm/method, we outline the main motivation behind its development, its inner workings, and its limitations. The presentation of the paper is aligned with the historical progress of the field, from the early 1980s Q-learning algorithm to the current state-of-the-art algorithms such as TD3, PPO, and offline RL. Overall, this paper aims to serve as a valuable resource for beginners looking to construct a solid understanding of the fundamentals of RL and be aware of the historical progress of the field. It is intended to be a go -to reference for those interested in learning about RL without being distracted by the details of specific applications. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Penetrating the Silence: Data Exfiltration in Maritime and Underwater Scenarios

TechRxiv

引用

TechRxiv 2023年

作者： Cantelli-Forti, Alessandro Colajanni, Michele Russo, Silvio Radar and Surveillance Systems National Laboratory CNIT Pisa Italy Department of Computer Science and Engineering University of Bologna Bologna Italy

The risk of data exfiltration remains a concern, even when the connectivity of the victim system is limited or the domain is physically isolated. This paper delves into the unique challenges associated with data exfiltration in surface and submarine naval scenarios in the absence of persistent data connections. It explores contexts where attacks through the supply chain can pose a serious risk even if the compromised hardware or software is not connected to any network or even (apparently) switched off. The attacks exploiting vulnerabilities in some components of the supply chain can serve as a conduit for data exfiltration. This study aims to enhance the overall security posture of maritime systems by identifying possible exposures and mitigating the risk of data exfiltration and covered channel attacks. © 2023, CC BY-NC-SA.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Hierarchical adaptive value estimation for multi-modal visual reinforcement learning 23

Hierarchical adaptive value estimation for multi-modal visua...

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Yangru Huang Peixi Peng Yifan Zhao Haoran Xu Mengyue Geng Yonghong Tian School of Computer Science Peking University School of Electronic and Computer Engineering Shenzhen Graduate School Peking University and Peng Cheng Laboratory Peng Cheng Laboratory and School of Intelligent Systems Engineering Sun Yat-sen University School of Computer Science Peking University and School of Electronic and Computer Engineering Shenzhen Graduate School Peking University and Peng Cheng Laboratory

Integrating RGB frames with alternative modality inputs is gaining increasing traction in many vision-based reinforcement learning (RL) applications. Existing multi-modal vision-based RL methods usually follow a Global Value Estimation (GVE) pipeline, which uses a fused modality feature to obtain a unified global environmental description. However, such a feature-level fusion paradigm with a single critic may fall short in policy learning as it tends to overlook the distinct values of each modality. To remedy this, this paper proposes a Local modality-customized Value Estimation (LVE) paradigm, which dynamically estimates the contribution and adjusts the importance weight of each modality from a value-level perspective. Furthermore, a task-contextual re-fusion process is developed to achieve a task-level re-balance of estimations from both feature and value levels. To this end, a Hierarchical Adaptive Value Estimation (HAVE) framework is formed, which adaptively coordinates the contributions of individual modalities as well as their collective efficacy. Agents trained by HAVE are able to exploit the unique characteristics of various modalities while capturing their intricate interactions, achieving substantially improved performance. We specifically highlight the potency of our approach within the challenging landscape of autonomous driving, utilizing the CARLA benchmark with neuromorphic event and depth data to demonstrate HAVE's capability and the effectiveness of its distinct components. The code of our paper can be found at https://***/Yara-HYR/HAVE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High isolation and gain metamaterial based MIMO antenna for 5G millimiter wave applications

High isolation and gain metamaterial based MIMO antenna for ...

引用

2024 International Conference on Circuit, systems and Communication, ICCSC 2024

作者： Elalaouy, Ouafae Aghoutane, Bilal El Ghzaoui, Mohammed Das, Sudipta Foshi, Jaouad El Faylali, Hanan University of Moulay Ismail Faculty of Sciences and Techniques Errachidia Errachidia Morocco Faculty of Sciences IbnTofail University Informatics Systems and Optimization Laboratory Department of Computer Science Kenitra Morocco Sidi Mohamed Ben Abdellah University Faculty of Sciences Dhar El Mahraz Fes Morocco Imps College of Engineering and Technology Department of Electronics and Communication Engineering W.B Malda India

ISBN: (纸本)9798350365306

In the contemporary era, harnessing millimeter-wave frequencies emerges as a compelling strategy to fulfill the swift data transfer requirements for 5G communications. Consequently, this study involves designing a metamaterial-based multiple-input multiple-output (MIMO) antenna with a focus on achieving high isolation and gain within the millimeter-wave spectrum. The suggested MIMO is printed on a Rogers RT5800 measuring 18 × 38 × 0.8 mm3. The single antenna element demonstrates a broad frequency coverage from 27.2 to 28.72GHz. To elevate the antenna's effectiveness, a two-port MIMO configuration is implemented by introducing a second antenna element parallel to benchmark antenna. However, the isolation between the two elements is deemed satisfactory. To address this, a 4 × 1 metamaterial unit cell is introduced, significantly enhancing isolation from 31 dB to 39 dB at 28 GHz. Furthermore, it improves the gain by 0.5 dBi at 28 GHz, elevating it from 8.5 to 9 dBi. The collective features of the suggested two ports MIMO antenna, encompassing its compactness and simplicity, position it as an excellent option for upcoming portable and shrink devices in Internet of Things uses. © 2024 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

All-optical logic gates based on hierarchical photonic crystal modulated photoluminescence of perovskite nanocrystals

引用

science China(Technological sciences) 2023年第9期66卷 2735-2742页

作者： WANG Yun ZHA YanFang YANG YunYi LIU CiHui DI YunSong CAO GuiYuan WEI ShiBiao CHEN ZhiHui GAN ZhiXing Center for Future Optoelectronic Functional Materials School of Computer and Electronic InformationSchool of Artificial IntelligenceNanjing Normal UniversityNanjing 210023China Centre for Translational Atomaterials School of ScienceSwinburne University of TechnologyHawthorn VIC 3122Australia Nanophotonics Research Center Shenzhen Key Laboratory of Micro-Scale Optical Information TechnologyShenzhen UniversityShenzhen 518060China Key Laboratory of Advanced Transducers and Intelligent Control Systems Ministry of Education and Shanxi ProvinceCollege of Electronic Information and Optical EngineeringTaiyuan University of TechnologyTaiyuan 030024China

Halide perovskites exhibit high performance in all sorts of optoelectronic and photonic areas, suggesting their huge potential in integrated photonic devices. However, until now, all optical logic gates based on perovskites are still rarely explored, hindering the development of all-optical networks and computing. Herein, a new concept of all-optical logic gates is proposed based on the modulation of photoluminescence(PL) from perovskite nanocrystals(PNCs). A hierarchical photonic crystal(Hie PhC) is developed by self-assembling polystyrene(PS) and SiO2nanoparticles, which exhibit a higher PL enhancement than that of a monolayer PhC. Moreover, the light-controlled PL is realized by taking advantage of the high thermal response of the PL from PNCs/Hie PhC on polyethylene(PE) substrate, assisted by a graphene layer for light-heat conversion. Consequently, optical diode and triode are achieved based on the modulated PL, which exhibit contrast ratios(CR) of 24.7 and 74.0 dB, ***-optical logic gates, including “AND”, “OR” and “NOT”, are realized based on the optical diode and triode.

关键词： perovskite nanocrystals photonic crystals all-optical logic gates modulation of photoluminescence

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：