教学课程资源库 更多>>

关键词： Training   Games   Data models   Computer science   Servers   Resource management   Federated learning   Optimization   Privacy   Energy consumption   Stackelberg game   resource allocation   incentive mechanism   federated learning  

摘要： Federated learning (FL) is an emerging distributed-learning technology that allows a requester to hire a set of independent FL workers for a model training task. The fact that FL workers are not obliged to do the training task calls for an incentive mechanism to motivate workers. However, existing incentive mechanisms for FL mainly were designed for single requester. A few studies considered multiple requesters but constrained a worker's potential to train multiple models simultaneously. In this paper, we remove the constraint to investigate the interplays among requesters in addition to inherent interplays among workers and between requesters and workers. Two crucial issues in this setting are whether the interplays lead to a stable (i.e., attainable) outcome and how to find it. We model the problem as seeking an equilibrium in a multi-leader multi-follower Stackelberg game and propose an exact method based on the derivation and backward induction to identify the Stackelberg equilibrium. We show how to adapt the proposed method to scenarios with capacity/budget constraints and privacy concerns. We have done a series of analyses to study the interplays of workers and requesters in Stackelberg equilibria. The results confirm the first-mover advantage of the requesters and reveal the possibility of mutual benefits between the requesters and workers.

关键词： Perturbation methods   Measurement   Observers   Predictive models   Distortion   Noise   Feature extraction   Computer science   Visualization   Visual systems   Adversarial stealthiness assessment   adversarial attack   classification  

摘要： Assessing the stealthiness of adversarial perturbations is challenging due to the lack of appropriate evaluation metrics. Existing evaluation metrics, e.g., L-p norms or Image Quality Assessment (IQA), fall short of assessing the pixel-level stealthiness of subtle adversarial perturbations since these metrics are primarily designed for traditional distortions. To bridge this gap, we present the first comprehensive study on the subjective and objective assessment of the stealthiness of adversarial perturbations from a visual perspective at a pixel level. Specifically, we propose new subjective assessment criteria for human observers to score adversarial stealthiness in a fine-grained manner. Then, we create a large-scale adversarial example dataset comprising 10586 pairs of clean and adversarial samples encompassing twelve state-of-the-art adversarial attacks. To obtain the subjective scores according to the proposed criterion, we recruit 60 human observers, and each adversarial example is evaluated by at least 15 observers. The mean opinion score of each adversarial example is utilized for labeling. Finally, we develop a three-stage objective scoring model that mimics human scoring habits to predict adversarial perturbation's stealthiness. Experimental results demonstrate that our objective model exhibits superior consistency with the human visual system, surpassing commonly employed metrics like PSNR and SSIM.

关键词： Artificial intelligence   scientific research   scientific research   science ethics   science ethics   computer science   computer science   physics   physics   medicine   medicine   psychology   psychology   mathematics   mathematics   geography   geography   agriculture   agriculture  

摘要： The recent rise in relevance and diffusion of Artificial Intelligence (AI)-based systems and the increasing number and power of applications of AI methods invites a profound reflection on the impact of these innovative systems on scientific research and society at large. The Universal Scientific Education and Research Network (USERN), an organization that promotes initiatives to support interdisciplinary science and education across borders and actively works to improve science policy, collects here the vision of its Advisory Board members, together with a selection of AI experts, to summarize how we see developments in this exciting technology impacting science and society in the foreseeable future. In this review, we first attempt to establish clear definitions of intelligence and consciousness, then provide an overview of AI's state of the art and its applications. A discussion of the implications, opportunities, and liabilities of the diffusion of AI for research in a few representative fields of science follows this. Finally, we address the potential risks of AI to modern society, suggest strategies for mitigating those risks, and present our conclusions and recommendations.

ISBN: (数字)9783111436425;9783111436579 ISBN: (纸本)9783111436388

摘要： Imaging Science consists of three core interconnected pillars – Image Processing, Computer Vision, and Pattern Recognition. This book showcases groundbreaking applications and provides solid foundation in the theoretical underpinnings and low-level processing techniques of each field. Dive into practical examples showcasing the power of pattern recognition algorithms and emerge equipped to contribute to the vibrant research communities.

关键词： Project management   Software   Organizations   Systematic literature review   Interviews   Cultural differences   Costs   Computer science   Technological innovation   Lead   GSD projects   CSFs   software project management   interrelationships   ISM   MICMAC  

摘要： In current era of technological advancement, global software development (GSD) is expanding to an increasing extent. This rise is driven by the advantages of low-cost development, access to expert resources, proximity to markets and clients, as well as options for innovation and the exchange of best practices. However, the various key aspects of GSD, including geographical dispersion, work ethics, time zone differences and cultural variability make project management more complex in a GSD setting. This study harnesses the critical success factors (CSFs) approach to identify the model for successful management of GSD projects. Sixteen CSFs have been determined using literature review, expert judgement, and exhaustive interviews. The interrelationship among the identified CSFs has been modeled using interpretive structural modeling (ISM) and cross-impact matrix multiplication applied to classification (MICMAC) analysis. The proposed model has been validated using detailed interviews, conducted with twelve professionals from industry and academia. The expert participants were carefully chosen based on criteria which include working experience, roles, and participation in GSD projects. This research computes CSFs of software project management in GSD by assessing their driving and relative strengths. Furthermore, these CSFs are categorized using MICMAC analysis. The previous research studies lack in exploring the mutual influence of CSFs and their hierarchical relationships. With the application of ISM and MICMAC analysis, the proposed study offers understanding of these interdependencies, providing great insights into their driving and dependent function. These insights enhance knowledge in GSD project management by allowing practitioners to prioritize key criteria and formulate potent management strategies.

关键词： Chatbots   Artificial intelligence   Measurement   Education   Computer science   Writing   Object recognition   Electrical engineering   Translation   Robot sensing systems   ChatGPT   education   LLM   computer science and engineering   electrical engineering  

摘要： Large Language Models (LLMs) like ChatGPT have become the most popular regenerative AI applications, used for obtaining responses for queries in different domains. The responses of ChatGPT are already becoming mainstream and are challenging conventional methods of learning. This article focuses on the application of ChatGPT for academic instructional purposes in the field of computer engineering and related majors. The capability of ChatGPT for instructional purposes is evaluated based on the responses to different questions about these engineering streams. This article explores different opportunities (with use cases), that ChatGPT can provide in augmenting the learning experience. It also provides scenarios of limitations and modifying the evaluation process to prevent the use of ChatGPT, which may lead to an inaccurate dissemination of accepted facts. In this paper, common classroom problems and their respective responses from ChatGPT in the domains of Computer Science, Cyber Security, Data Science, and Electrical Engineering are analyzed to determine the categories of queries for which ChatGPT offers reliable responses and those for which it may be factually incorrect. A student survey is performed to demonstrate that students must be made aware that ChatGPT may not be suitable for certain types of queries and means of upgrading the evaluation process.

关键词： Knowledge engineering   Semantics   Data models   Predictive models   Attention mechanisms   Self-supervised learning   Analytical models   Deep learning   Computer science   Computational modeling   Intelligent systems   self-supervised learning   attention mechanisms   graph convolutional networks   knowledge tracing  

摘要： As intelligent education advances and online learning becomes more prevalent, Knowledge Tracing (KT) has become increasingly important. KT assesses students' learning progress by analysing their historical performance in related exercises. Despite significant advances in the field, there are still shortcomings in two aspects: first, a lack of effective integration between exercises and knowledge points;second, an overemphasis on nodal information, neglecting deep semantic relationships. To address these, we propose a self-supervised learning approach that uses an enhanced heterogeneous graph attention network to represent and analyse complex relationships between exercises and knowledge points. We introduce an innovative surrogate view generation method to optimise the integration of local structural information and global semantics within the graph, addressing relational inductive bias. In addition, we incorporate the improved representation algorithm into the loss function to handle data sparsity, thereby improving prediction accuracy. Experiments on three real-world datasets show that our model outperforms baseline models.

关键词： Stock markets   Portfolios   Data models   Prediction algorithms   Profitability   Indexes   Heuristic algorithms   Deep reinforcement learning   Computer science   Supervised learning   Deep reinforcement learning (DRL)   stock market trading   portfolio management   max drawdown rewards   advantage actor-critic (A2C)   deep deterministic policy gradient (DDPG)   proximal policy optimization (PPO)  

摘要： Algorithmic stock trading has improved tremendously, with Reinforcement Learning (RL) algorithms being more adaptable than classic approaches like mean reversion and momentum. However, challenges remain in adequately depicting market events and generating suitable rewards to influence the trading decisions of an agent in a dynamic environment. This study proposed an improved stock market trading framework termed the RMS-Driven Deep Reinforcement Learning (DRL) model for optimal portfolio management. The research attempts to give a more comprehensive view of the market and, as a result, enhance trading decisions by including consumer information and incorporating news sentiments into the model, in addition to data from typical earnings reports. More specifically, three kinds of DRL models are presented, combined with data from stock earnings reports, Max Drawdown rewards, and sentiment indicators (RMS), known as PPO_RMS, A2C_RMS, and DDPG_RMS, respectively. The findings of this research indicate that the integrated model, mainly the DDPG_RMS effectively outperforms the baseline <^>DJI index in many risk-return analyses in ratios showing better risk management, and profitability. The proposed stock trading model generates a maximum cumulative return of 27% with a Sharpe ratio of 0.66, showing an appropriate trade-off between risk and return. This approach, which incorporates sentiment analysis and Max Drawdown rewards, significantly enhances the model's performance in adapting to changing market conditions. Therefore, the results emphasize the appropriateness of integrating sentiment indices with traditional financial data to enhance a trader's performance while also offering essential information to aid in the development of improved trading tactics in continuously changing financial markets.

关键词： postdoctoral   mentorship   content analysis   engineering   computer science  

摘要： Postdoctoral training holds an increasingly important position in securing high-impact research and academic positions in engineering and computer science. High-quality mentorship contributes to the success of postdoctoral trainees, but existing literature demonstrates postdocs from outside of the US, women, and racial minorities who experience stereotypes are provided less mentorship, and less successful outcomes than their white and male counterparts. Further, trainees who originate from outside of the US hold more than half of the postdoctoral positions in the US. Increasingly, funding agencies within the US require postdoctoral mentorship plans, but it is unclear to what end and if they are helpful or simply performative. Specifically, to date, no research has investigated the content of mentorship plans, their alignment to theory and existing research, or the needs of postdoctoral trainees particularly those from outside of the US, women, and racial minorities. As part of a larger project investigating postdoctoral mentorship, we analyzed 54 postdoctoral mentoring plans to identify how they align with recommendations from content supported by theory and literature. We find marginal alignment with best practices, with much room for improvement, including tailoring and specificity. From this work, a postdoctoral mentorship blueprint and rubric for plan evaluation are offered as tools to improve the uniqueness, specificity, and utility of mentorship plans.

关键词： Surveys   Engineering profession   Psychology   Computer science   STEM   Particle measurements   Ethnicity   Cause effect analysis   Atmospheric measurements   Analysis of variance   Applied research   basic research   computing education   gender  

摘要： Women remain under-represented in academic science, and this is especially true in computing. While there is limited research on gender differences in research focus, there is evidence that women may be more likely to conduct applied research. We surveyed tenured and tenure-track faculty in the United States to understand perceptions of hypothetical researchers who engage in applied or theoretical work. Faculty rated researchers engaged in applied research as less likely to publish their work, receive tenure/be promoted, obtain awards, and get funding for their work. Faculty further rated these researchers as less brilliant, creative, and technically skilled than they rated their theory-focused counterparts. Data from publications, hiring, funding, and awards suggests that applied research may indeed lead to worse career outcomes. We further show that women are more highly represented in applied research areas than theoretical ones. Negative perceptions of applied researchers must now be addressed to avoid exacerbating the gender gap.