检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Jiang, Bo Liu, Ya-Feng Ministry of Education Key Laboratory of NSLSCS School of Mathematical Sciences Nanjing Normal University Nanjing210023 China State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781713899921

Projection robust Wasserstein (PRW) distance is recently proposed to efficiently mitigate the curse of dimensionality in the classical Wasserstein distance. In this paper, by equivalently reformulating the computation of the PRW distance as an optimization problem over the Cartesian product of the Stiefel manifold and the Euclidean space with additional nonlinear inequality constraints, we propose a Riemannian exponential augmented Lagrangian method (REALM) for solving this problem. Compared with the existing Riemannian exponential penalty-based approaches, REALM can potentially avoid too small penalty parameters and exhibit more stable numerical performance. To solve the subproblems in REALM efficiently, we design an inexact Riemannian Barzilai-Borwein method with Sinkhorn iteration (iRBBS), which selects the stepsizes adaptively rather than tuning the stepsizes in efforts as done in the existing methods. We show that iRBBS can return an Ε-stationary point of the original PRW distance problem within O(Ε-3) iterations, which matches the best known iteration complexity result. Extensive numerical results demonstrate that our proposed methods outperform the state-of-the-art solvers for computing the PRW distance. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Tree-based Parallel Algorithms for N-Body Simulations Using C++ Standard Parallelism

Efficient Tree-based Parallel Algorithms for N-Body Simulati...

引用

2024 Workshops of the International Conference for High Performance computing, Networking, Storage and Analysis, SC Workshops 2024

作者： Cassell, Thomas Lane Deakin, Tom Alpay, Aksel Heuveline, Vincent Gadeschi, Gonzalo Brito University of Bristol School of Computer Science BristolBS8 1UB United Kingdom Heidelberg University Engineering Mathematics and Computing Lab Interdisciplinary Center for Scientific Computing Heidelberg Germany NVIDIA GPU Architecture Munich Germany

ISBN: (纸本)9798350355543

The Barnes-Hut approximation for N-body simulations reduces the time complexity of the naive all-pairs approach from O(N2) to O(N log N) by hierarchically aggregating nearby particles into single entities using a tree data structure. This inherently irregular algorithm poses substantial challenges for performance portable implementations on multi-core CPUs and GPUs. We introduce two portable fully-parallel Barnes-Hut implementation strategies that trade-off different levels of GPU support for performance: an unbalanced concurrent octree, and a balanced bounding volume hierarchy sorted by a Hilbert spacefilling curve. We implement these algorithms in portable ISO C++ using parallel algorithms and concurrency primitives like atomics. The results demonstrate competitive performance on a range of CPUs and GPUs. Additionally, they highlight the effectiveness of the par execution policy for highly concurrent irregular algorithms, outperforming par_unseq on CPUs and GPUs with Independent Thread Scheduling. © 2024 IEEE.

关键词： n/a

来源：评论

学校读者我要写书评

暂无评论

Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review

Benchmarks and Metrics for Evaluations of Code Generation: A...

引用

IEEE International Conference on Artificial Intelligence Testing (AITest)

作者： Debalina Ghosh Paul Hong Zhu Ian Bayley School of Engineering Computing and Mathematics Oxford Brookes University Oxford UK

ISBN: (数字)9798350365054

ISBN: (纸本)9798350365061

With the rapid development of Large Language Models (LLMs), a large number of machine learning models have been developed to assist programming tasks including the generation of program code from natural language input. However, how to evaluate such LLMs for this task is still an open problem despite of the great amount of research efforts that have been made and reported to evaluate and compare them. This paper provides a critical review of the existing work on the testing and evaluation of these tools with a focus on two key aspects: the benchmarks and the metrics used in the evaluations. Based on the review, further research directions are discussed.

关键词： Measurement Codes Automation Reviews Large language models Natural languages Machine learning

来源：评论

学校读者我要写书评

暂无评论

ScenEval: A Benchmark for Scenario-Based Evaluation of Code Generation

ScenEval: A Benchmark for Scenario-Based Evaluation of Code ...

引用

IEEE International Conference on Artificial Intelligence Testing (AITest)

作者： Debalina Ghosh Paul Hong Zhu Ian Bayley School of Engineering Computing and Mathematics Oxford Brookes University Oxford UK

ISBN: (数字)9798350365054

ISBN: (纸本)9798350365061

In the scenario-based evaluation of machine learning models, a key problem is how to construct test datasets that represent various scenarios. The methodology proposed in this paper is to construct a benchmark and attach metadata to each test case. Then a test system can be constructed with test morphisms that filter the test cases based on metadata to form a dataset. The paper demonstrates this methodology with large language models for code generation. A benchmark called ScenEval is constructed from problems in textbooks, an online tutorial website and Stack Overflow. Filtering by scenario is demonstrated and the test sets are used to evaluate ChatGPT for Java code generation. Our experiments found that the performance of ChatGPT decreases with the complexity of the coding task. It is weakest for advanced topics like multi-threading, data structure algorithms and recursive methods. The Java code generated by ChatGPT tends to be much shorter than reference solution in terms of number of lines, while it is more likely to be more complex in both cyclomatic and cognitive complexity metrics, if the generated code is correct. However, the generated code is more likely to be less complex than the reference solution if the code is incorrect.

关键词： Measurement Java Codes Tutorials Manuals Metadata Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Industrial Control Anomaly Detection Based on Distributed Linear Deep Learning

引用

Computers, Materials & Continua 2025年第1期82卷 1129-1150页

作者： Shijie Tang Yong Ding Huiyong Wang School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin541004China School of Electronic Engineering and Automation Guilin University of Electronic TechnologyGuilin541004China Guangxi Engineering Research Center of Industrial Internet Security and Blockchain Guilin University of Electronic TechnologyGuilin541004China Institute of Cyberspace Technology HKCT Institute for Higher EducationHong Kong999077China School of Mathematics&Computing Science Guilin University of Electronic TechnologyGuilin541004China

As more and more devices in Cyber-Physical Systems(CPS)are connected to the Internet,physical components such as programmable logic controller(PLC),sensors,and actuators are facing greater risks of network attacks,and fast and accurate attack detection techniques are *** key problem in distinguishing between normal and abnormal sequences is to model sequential changes in a large and diverse field of time *** address this issue,we propose an anomaly detection method based on distributed deep *** method uses a bilateral filtering algorithm for sequential sequences to remove noise in the time series,which can maintain the edge of discrete *** use a distributed linear deep learning model to establish a sequential prediction model and adjust the threshold for anomaly detection based on the prediction error of the validation *** method can not only detect abnormal attacks but also locate the sensors that cause *** conducted experiments on the Secure Water Treatment(SWAT)and Water Distribution(WADI)public *** experimental results show that our method is superior to the baseline method in identifying the types of attacks and detecting efficiency.

关键词： Anomaly detection CPS deep learning MLP(multi-layer perceptron)

来源：评论

学校读者我要写书评

暂无评论

5G and Beyond: On the Significance of Wireless Channel Estimation

5G and Beyond: On the Significance of Wireless Channel Estim...

引用

IEEE Southeastcon

作者： Jasneet Kaur M. Arif Khan School of Computing Mathematics and Engineering Charles Sturt University NSW Australia

Wireless channel is one of the most important components of any wireless communication system. Accurate wireless channel knowledge at the transmitter ensures that correct amount of data is being transmitted to the intended users/devices in the system. This wireless channel knowledge, known as Channel State Information (CSI), is acquired at the transmitter through the feedback sent by the users/devices. The transmitter, then, uses this CSI to adjust the transmission, both in terms of data rate and direction, to the intended users/devices. In this paper, we investigated why accurate Wireless Channel Estimation (WCE) is even more critical for contemporary wireless technologies such as 5G and beyond? We first modelled the wireless channel between a transmitter and multiple receivers having multiple antennas using independent and identically distributed Gaussian random processes and calculated channel strengths and angle of transmission using ground as our azimuth reference. We then used a Simple Random Estimation (SRE) technique at the transmitter to estimate the same wireless channel. Our numerical results show that a small perturbation in WCE leads to significant deviations in channel strengths and directions. These estimation errors at the transmitter result in data loss as well as poor Quality of Service (QoS) to the users/devices. This study leads us to develop innovative wireless channel estimation techniques using Machine Learning (ML) at the transmitter that will reduce the amount of CSI feedback and improves the over all transmission in terms of both channel strengths and direction of transmission in our future work. Comment: given the purpose of this paper is to discuss channel estimation but in this paper we are not using specific baseline channel estimation techniques. Our main purpose is to show the channel error using SRE and future need to minimise this channel error.

关键词：

来源：评论

学校读者我要写书评

暂无评论

P-Box Design in Lightweight Block Ciphers: Leveraging Nonlinear Feedback Shift Registers

P-Box Design in Lightweight Block Ciphers: Leveraging Nonlin...

引用

IEEE Conference on Wireless Communications and Networking

作者： Muhammad Rana Quazi Mamun Rafiqul Islam School of Computing Mathematics and Engineering Charles Sturt University NSW Australia

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

In lightweight block cipher design, generating permutation boxes (P-boxes) is critical to security and efficiency. This paper introduces an innovative approach to P-box generation by integrating nonlinear feedback shift registers (NFSRs) to enhance cryptographic strength. NFSRs are known for their capacity to generate obscure and unpredictable sequences, making them a promising candidate for improving P-box design. This research investigates the intricacies of this novel method, highlighting its potential benefits and implementation challenges. The proposed NFSR-based P-box generation method offers improved diffusion properties, presenting an attractive option for creating secure and efficient lightweight block ciphers.

关键词： Ciphers Ecosystems Linearity Shift registers Resilience Pragmatics

来源：评论

学校读者我要写书评

暂无评论

CL3: A COLLABORATIVE LEARNING FRAMEWORK FOR THE MEDICAL DATA ENSURING DATA PRIVACY IN THE HYPERCONNECTED ENVIRONMENT

arXiv

引用

arXiv 2024年

作者： Parvez, Mohamamd Zavid Islam, Rafiqul Islam, Md Zahidul School of Computing Mathematics and Engineering Charles Sturt University NSW Australia

In a hyperconnected environment, medical institutions are particularly concerned with data privacy when sharing and transmitting sensitive patient information due to the risk of data breaches, where malicious actors could intercept sensitive information. A collaborative learning framework, including transfer, federated, and incremental learning, can generate efficient, secure, and scalable models while requiring less computation, maintaining patient data privacy, and ensuring an up-to-date model. This study aims to address the detection of COVID-19 using chest X-ray images through a proposed collaborative learning framework called CL3. Initially, transfer learning is employed, leveraging knowledge from a pre-trained model as the starting global model. Local models from different medical institutes are then integrated, and a new global model is constructed to adapt to any data drift observed in the local models. Additionally, incremental learning is considered, allowing continuous adaptation to new medical data without forgetting previously learned information. Experimental results demonstrate that the CL3 framework achieved a global accuracy of 89.99% when using Xception with a batch size of 16 after being trained for six federated communication rounds. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Modelling LCR-Circuit into Integro-Differential Equation Using Variational Iteration Method and GRU-Based Recurrent Neural Network 3

Modelling LCR-Circuit into Integro-Differential Equation Usi...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Thota, Srinivasarao Gopisairam, Tanneeru Bikku, Thulasi Amrita School of Physical Sciences Amrita Vishwa Vidyapeetham Department of Mathematics Andhra Pradesh Amaravati India Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Andhra Pradesh Amaravati India

ISBN: (纸本)9798331518592

This investigation incorporates digital numerical methods with neural networks for resolving an LCR circuit that shades the integro-differential equation. The variational iteration technique is needed to tackle numerical troubles. The One-Hidden Layer Gated Recurrent Unit (GRU) in a Recurrent Neural Network (RNN) is utilized to model and predict dynamic systems. This eidetic procedure is used as an example in the methodology of imaging dynamic systems and the development of the hybrid method. The advantage of this new tool is that it can be utilized in various contexts, especially in those areas where complex and continuous processes are frequent. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches to Indoor Wireless Channel Estimation for Low-Power Communication

Deep Learning Approaches to Indoor Wireless Channel Estimati...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Samrah Arif M. Arif Khan Sabih ur Rehman School of Computing Mathematics and Engineering Charles Sturt University NSW Australia

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

In the rapidly growing development of the Inter-net of Things (IoT) infrastructure, achieving reliable wireless communication is a challenge. ioT devices operate in diverse environments with common signal interference and fluctuating channel conditions. Accurate channel estimation helps adapt the transmission strategies to current conditions, ensuring reliable communication. Traditional methods, such as Least Squares (LS) and Minimum Mean Squared Error (MMSE) estimation techniques, often struggle to adapt to the diverse and complex environments typical of IoT networks. This research article delves into the potential of Deep Learning (DL) to enhance channel esti-mation, focusing on the Received Signal Strength Indicator (RSSI) metric - a critical yet challenging aspect due to its susceptibility to noise and environmental factors. This paper presents two Fully Connected Neural Networks (FCNNs)-based Low Power (LP-IoT) channel estimation models, leveraging RSSI for accurate channel estimation in LP-IoT communication. Our Model A exhibits a remarkable 99.02% reduction in Mean Squared Error (MSE), and Model B demonstrates a notable 90.03% MSE reduction compared to the benchmarks set by current studies. Additionally, the comparative studies of our model A with other DL-based techniques show significant efficiency in our estimation models.

关键词： Wireless communication Deep learning Accuracy Conferences Noise Channel estimation Estimation

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：