检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xuan, Yuner Chalmers University of Technology Computer Science and Engineering Department Gothenburg Sweden

It is always a challenge for recommender systems to give high-quality outcomes to cold-start users. One potential solution to alleviate the data sparsity problem for cold-start users in the target domain is to add data from the auxiliary domain. Finding a proper way to extract knowledge from an auxiliary domain and transfer it into a target domain is one of the main objectives for cross-domain recommendation (CDR) research. Among the existing methods, mapping approach is a popular one to implement cross-domain recommendation models (CDRs). For models of this type, a mapping module plays the role of transforming data from one domain to another. It primarily determines the performance of mapping approach CDRs. Recently, diffusion probability models (DPMs) have achieved impressive success for image synthesis related tasks. They involve recovering images from noise-added samples, which can be viewed as a data transformation process with outstanding performance. To further enhance the performance of CDRs, we first reveal the potential connection between DPMs and mapping modules of CDRs, and then propose a novel CDR model named Diffusion Cross-domain Recommendation (DiffCDR)1. More specifically, we first adopt the theory of DPM and design a Diffusion Module (DIM), which generates user's embedding in target domain. To reduce the negative impact of randomness introduced in DIM and improve the stability, we employ an Alignment Module to produce the aligned user embeddings. In addition, we consider the label data of the target domain and form the task-oriented loss function, which enables our DiffCDR to adapt to specific tasks. By conducting extensive experiments on datasets collected from reality, we demonstrate the effectiveness and adaptability of DiffCDR to outperform baseline models on various CDR tasks in both cold-start and warm-start scenarios. © 2024, CC BY.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

ChatGPT Has Eaten My Assignment: A Student-Centric Experiment on Supervising Writing Processes in the AI Era

ChatGPT Has Eaten My Assignment: A Student-Centric Experimen...

引用

IEEE Education engineering (EDUCON)

作者： Romaric Duvignau Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (数字)9798350394023

ISBN: (纸本)9798350394030

AI-powered text generation tools have brought about a profound shift in students' approaches to writing assignments, prompting the need for writing supervisors to gain a deeper understanding of how these tools can effectively tackle conventional university assignments. This ongoing work presents a documented and student-centered experiment where such tools are used for crafting the final assignment in a higher education course. Through the lens of a reflective essay, the study provides insights into the experiment's nuances and offers practical considerations that can prove invaluable to writing supervisors. Despite being introduced in late 2022, ChatGPT, a prominent AI language model, has quickly become a focal point in higher education research. This work distinguishes itself from existing literature by presenting a practical guide tailored for writing supervisors involved in overseeing diverse writing processes. By documenting a student's firsthand experience using ChatGPT to generate a self-assessment plan within the context of a university writing supervision course, the study not only explores the benefits and challenges of integrating AI tools but also underscores the importance of responsible usage. In particular, this work furnishes valuable insights for writing supervisors navigating the evolving landscape of AI-driven writing tools, offering a nuanced understanding of their practical implications.

关键词： Navigation Writing Chatbots Educational courses Artificial intelligence engineering education Lenses

来源：评论

学校读者我要写书评

暂无评论

Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs

arXiv

引用

arXiv 2024年

作者： Qararyah, Fareed Azhar, Muhammad Waqar Maleki, Mohammad Ali Trancoso, Pedro Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

Depthwise and pointwise convolutions have fewer parameters and perform fewer operations than standard convolutions. As a result, they have become increasingly used in various compact DNNs, including convolutional neural networks (CNNs) and vision transformers (ViTs). However, they have a lower compute-to-memory-access ratio than standard convolutions, making their memory accesses often the performance bottleneck. This paper explores fusing depthwise and pointwise convolutions to overcome the memory access bottleneck. The focus is on fusing these operators on GPUs. The prior art on GPU-based fusion suffers from one or more of the following: (1) fusing either a convolution with an element-wise or multiple non-convolutional operators, (2) not explicitly optimizing for memory accesses, (3) not supporting depthwise convolutions. This paper proposes Fused Convolutional Modules (FCMs), a set of novel fused depthwise and pointwise GPU kernels. FCMs significantly reduce pointwise and depthwise convolutions memory accesses, improving execution time and energy efficiency. To evaluate the tradeoffs associated with fusion and determine which convolutions are beneficial to fuse and the optimal FCM parameters, we propose FusePlanner. FusePlanner consists of cost models to estimate the memory accesses of depthwise, pointwise, and FCM kernels given GPU characteristics. Our experiments on three GPUs using representative CNNs and ViTs demonstrate that FCMs save up to 83% of the memory accesses and achieve speedups of up to 3.7x compared to cuDNN. Complete model implementations of various CNNs using our modules outperform TVMs’ achieving speedups of up to 1.8x and saving up to two-thirds of the energy. FCM and FusePlanner implementations are open source: https://***/fqararyah/Fusing_DW_and_PW_on_GPUs © 2024, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Generalised Active Learning With Annotation Quality Selection 33

Generalised Active Learning With Annotation Quality Selectio...

引用

33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023

作者： Lindqvist, Jakob Olmin, Amanda Svensson, Lennart Lindsten, Fredrik Chalmers University of Technology Dept. of Electrical Engineering Gothenburg Sweden Linköping University Dept. of Computer and Information Science Linköping Sweden

ISBN: (纸本)9798350324112

In this paper we promote a general formulation of active learning (AL), wherein the typically binary decision to annotate a point or not is extended to selecting the qualities with which the points should be annotated. By linking the annotation quality to the cost of acquiring the label, we can trade a lower quality for a larger set of training samples, which may improve learning for the same annotation cost. To investigate this AL formulation, we introduce a concrete criterion, based on the mutual information (MI) between model parameters and noisy labels, for selecting annotation qualities for the entire dataset, before any labels are acquired. We illustrate the usefulness of our formulation with examples for both classification and regression and find that MI is a good candidate for a criterion, but its complexity limits its usefulness. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

How to Better Teach computer Networks to Freshman Engineers Post-Pandemic, A Case Study

How to Better Teach Computer Networks to Freshman Engineers ...

引用

IEEE Education engineering (EDUCON)

作者： Romaric Duvignau Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (数字)9798350394023

ISBN: (纸本)9798350394030

The landscape of higher education experienced a significant transformation due to the COVID-19 pandemic, prompting a swift shift from traditional in-class models to online formats. With the return of courses to on-campus delivery, educators now have a distinct opportunity to contemplate teaching methodologies. Our case study delves into the post-pandemic changes within an introductory and sizable networking course, specifically concentrating on optimizing computer network instruction for first-year engineering students. While prior research has explored lessons learned from the pandemic and the increased adoption of digital education, a notable gap exists in the literature concerning labs, particularly the transition from remote to physical content. The primary objective of the study is to guide a more balanced allocation of student learning time in the post-COVID era, aiming to minimize frustration by refining lab activities for equivalent learning outcomes. To enhance student comprehension of networking protocols, we implemented updates, capitalizing on the shift to campus education and employing three pedagogical approaches: Active Learning (AL), Practice Test/Spaced Practice (PT/SP), and Peer Instructions (PI). These updates were driven by three specific objectives: establishing new physical labs including collaboration between groups to foster PI and AL, conducting beneficial in-class exercises to facilitate live PI and enhance a PT/SP approach, and transitioning to in-class quizzes to evaluate AL between online and in-person lectures. Feedback collected through surveys, statistics from the learning management system, and quiz applications indicates that the updates successfully achieved their objectives. The study offers nuanced reflections and valuable insights into enhancing student understanding of networking protocols in the post-COVID era, emphasizing a balanced distribution of learning time and minimizing frustration associated with lab activities.

关键词： Surveys Learning management systems Protocols Pandemics Computational modeling Refining computer networks

来源：评论

学校读者我要写书评

暂无评论

An Analytical Cost Model for Fast Evaluation of Multiple Compute-Engine CNN Accelerators

arXiv

引用

arXiv 2025年

作者： Qararyah, Fareed Maleki, Mohammad Ali Trancoso, Pedro Department of Computer Science and Engineering Chalmers University of Technology University of Gothenburg Gothenburg Sweden

Convolutional Neural Networks (CNNs) serve various applications with diverse performance and resource requirements. Model-aware CNN accelerators best address these diverse requirements. These accelerators usually combine multiple dedicated Compute Engines (CEs). The flexibility of Field-Programmable Gate Arrays (FPGAs) enables the design of such multiple Compute-Engine (multiple-CE) accelerators. However, existing multiple-CE accelerators differ in how they arrange their CEs and distribute the FPGA resources and CNN operators among the CEs. The design space of multiple-CE accelerators comprises numerous such arrangements, which makes a systematic identification of the best ones an open challenge. This paper proposes a Multiple-CE accelerator analytical Cost Model (MCCM) and an evaluation methodology built around MCCM. The model and methodology streamline the expression of any multiple-CE accelerator and provide a fast evaluation of its performance and efficiency. MCCM is in the order of 100000× faster than traditional synthesis-based evaluation and has an average accuracy of > 90%. The paper presents three use cases of MCCM. The first describes an end-to-end evaluation of state-of-the-art multiple-CE accelerators considering various metrics, CNN models, and resource budgets. The second describes fine-grained evaluation that helps identify performance bottlenecks of multiple-CE accelerators. The third demonstrates that MCCM fast evaluation enables exploring the vast design space of multiple-CE accelerators. These use cases show that no unique CE arrangement achieves the best results given different metrics, CNN models, and resource budgets. They also show that fast evaluation enables design space exploration, resulting in accelerator designs that outperform state-of-the-art ones. MCCM is available at https://***/fqararyah/MCCM © 2025, CC BY.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

The Impact of Compiler Warnings on Code Quality in C++ Projects

The Impact of Compiler Warnings on Code Quality in C++ Proje...

引用

IEEE/ACM International Conference on Program Comprehension (ICPC)

作者： Albin Johansson Carl Holmberg Francisco G. de Oliveira Neto Philipp Leitner Dept. of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden Dept. of Computer Science and Engineering Chalmers | University of Gothenburg Gothenburg Sweden

ISBN: (数字)9798400705861

ISBN: (纸本)9798350352276

Modern compilers often offer a variety of warning flags, which developers can enable to get feedback on code that, while syntactically correct, may be problematic. In the case of C++, one example of such “correct but problematic” code is code that leads to undefined behavior (UB). The usage of compiler warnings has long been suspected as a way to decrease bugs and increase code quality. However, empirical evidence that supports this hypothesis is rare. In this study, we present evidence from a study of 127 open source C++ projects. We categorize their usage of compiler warnings into five groups based on which warning flags are being used, and analyse the relationship between compiler warnings and five quality metrics (bugs, critical issues, vulnerabilities, code smells, and technical debt) using Bayesian analysis. We conclude that, in general, compiler warnings indeed correlate with, and potentially cause, higher code quality, with the clearest impact being on the number of critical issues in a project. Using stricter warning flags expectantly correlates with higher code quality in our study objects. However, there are substantial differences between projects, which we attribute to the project’s individual development culture. That is, while warnings matter, other factors such as quality culture, are likely to be even more important to source code *** CONCEPTS • Software and its engineering $\rightarrow$ Maintaining software; Compilers; Software maintenance tools.

关键词： Measurement Software maintenance Codes Correlation Program processors Data analysis Source coding

来源：评论

学校读者我要写书评

暂无评论

To Be or Not to Be (in the EU): Measurement of Discrepancies Presented in Cookie Paywalls (LONG)

arXiv

引用

arXiv 2024年

作者： Stenwreth, Andreas Täng, Simon Morel, Victor Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

Cookie paywalls allow visitors to access the content of a website only after making a choice between paying a fee (paying option) or accepting tracking (cookie option). The practice has been studied in previous research in regard to its prevalence and legal standing, but the effects of the clients’ device and geographic location remain unexplored. To address these questions, this study explores the effects of three factors: 1) the clients’ browser, 2) the device type (desktop or mobile), and 3) the geographic location on the presence and behavior of cookie paywalls and the handling of users’ data. Using an automatic crawler on our dataset composed of 804 websites that present a cookie paywall, we observed that the presence of a cookie paywall was most affected by the geographic location of the user. We further showed that both the behavior of a cookie paywall and the processing of user data are impacted by all three factors, but no patterns of significance could be found. Finally, an additional type of paywall was discovered to be used on approximately 11% of the studied websites, coined the "double paywall", which consists of a cookie paywall complemented by another paywall once tracking is accepted. © 2024, CC BY.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

BZSim: Fast, Large-Scale Microarchitectural Simulation with Detailed Interconnect Modeling

BZSim: Fast, Large-Scale Microarchitectural Simulation with ...

引用

IEEE International Symposium on Performance Analysis of Systems and Software

作者： Panagiotis Strikos Ahsen Ejaz Ioannis Sourdis Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (数字)9798350376388

ISBN: (纸本)9798350376395

Modeling of on-chip interconnects in microarchitectural simulations is becoming more important. Chips continue to increase their number of cores, i.e., via 3D stacking and multi-chiplet integration, and their performance is gradually more affected by their network. However, existing simulation alternatives are either too slow for large systems or lack support for modeling interconnects, which is on its own a computationally intensive task. This work offers an open-source solution that integrates an accurate, widely used network simulator into an existing fast, parallel microarchitectural simulator enhanced with a new mechanism to make network modeling lightweight. It is based on the observation that a significant fraction of the network traffic has low contention and on the conjecture that the latency of such traffic can be calculated analytically with good accuracy. The proposed approach offers a mechanism to detect low contention traffic and analytically calculate its latency reducing the overheads of network simulation. In essence, it offers a knob for trading simulation accuracy for speed. This tradeoff is explored by demonstrating 2-4× faster simulations within 3-5% error in normalized IPC and 10-20% in average packet latency. Our simulation setup is an order of magnitude faster than an optimistic gem5 setup with point-to-point interconnects and 3× slower than a ZSim setup without network modeling. Our approach is further used to assess the impact of Networkon-Chip designs on system performance and shows that a 32-core system is on average 1.2× faster when using the current state of the art NoC instead of a baseline NoC.

关键词： Analytical models Accuracy Microarchitecture Three-dimensional displays Computational modeling System performance Stacking

来源：评论

学校读者我要写书评

暂无评论

Design Recommendations for Historical Cemeteries Using Speculative Design 22

Design Recommendations for Historical Cemeteries Using Specu...

引用

25th International Academic Mindtrek Conference, Academic Mindtrek 2022

作者： Hirsch, Linda Hild, Florian Obaid, Mohammad LMU Munich Munich Germany Chalmers University of Technology Gothenburg Sweden Interaction Design Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (纸本)9781450399555

Historical cemeteries are interesting design spaces within Human-computer Interaction (HCI), due to their cultural and personal significance, and that they also serve multi-purposes within an urban community. However, contemporary usage of such places and technological developments partly interfere with preserving such places' significance. To evaluate how to counteract this challenge, we conducted an iterative design approach including a) five expert interviews, b) a design workshop using speculative design artifacts (n=4), followed by c) semi-structured interviews that evaluated the derived design concepts (n=6). We made an exemplary study of a European historical cemetery, and consolidate ten design recommendations for interactive historical cemeteries. Eight align with prior work, two are new. Furthermore, we identified design opportunities for supportive technology to maintain such places' atmosphere and regulate users' behavior to comply with the local code of conduct. Our work supports other HCI researchers, aiming to preserve cultural heritage sites such as historical cemeteries. © 2022 ACM.

关键词： Human computer interaction

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：