检索结果-内蒙古大学图书馆

Congress on Evolutionary Computation

作者： Jiao Liu Yew Soon Ong Melvin Wong College of Computing & Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Recently, evolutionary multitasking has been employed to generate a “set of Pareto sets” (SOS) for machine learning models, addressing diverse task settings across heterogeneous environments. This involves creating a repository of compact, specialized solution models that are collectively tailored to each specific task setting and environment, enabling users to select the most suitable model based on particular specifications and preferences. In this paper, we further demonstrate the versatility and applicability of the SOS concept across diverse domains, focusing on three real-world problems: engineering design problems, inventory management problems, and hyperparameter optimization problems. Additionally, as evolutionary multitasking has proven effective in generating the SOS, we investigate the performance of current evolutionary multitasking methods on these real-world problems. Subsequently, we present visualizations of the generated SOS in both decision and objective spaces, complemented by the development of a measurement to gauge the similarity between different Pareto sets corresponding to diverse tasks. Finally, we show that by systematically examining the shifts in Pareto optimal designs across different task settings though the SOS solutions, users can gain deeper understandings on the dynamic interplay between design solutions and their performance in different settings or contexts.

关键词： Visualization Heuristic algorithms Focusing Pareto optimization Inventory management Multitasking Hyperparameter optimization

来源：评论

学校读者我要写书评

暂无评论

Robust Kernel Sparse Subspace Clustering

Robust Kernel Sparse Subspace Clustering

引用

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

作者： Ivica Kopriva Division of Computing and Data Science Rudjer Boskovich Institute Zagreb Croatia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Kernel methods are widely used in pattern recognition, including subspace clustering (SC). They transform nonlinear problems in the input data space into linear ones in a high-dimensional feature space. This transformation, achieved through the kernel trick, makes computationally tractable nonlinear algorithms possible. However, kernelizing linear algorithms through the kernel trick is infeasible in case of gross sparse corruptions that are modeled by the ℓ 1 -norm of the error term. To address this, we propose, for the first time, a robust kernel sparse SC (RKSSC) algorithm for data with gross sparse corruptions. We validated the proposed approach on two well-known datasets, using the linear robust SSC algorithm and nonlinear (kernel-based) SSC algorithm as baseline models. According to the Wilcoxon test, the RKSSC's algorithm clustering performance is statistically significantly better than baselines.

关键词： Computational modeling Clustering algorithms Signal processing algorithms Transforms Signal processing Pattern recognition Sparse matrices Kernel Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

Clause-level Relationship-aware Math Word Problems Solver

引用

Machine Intelligence Research 2022年第5期19卷 425-438页

作者： Chang-Yang Wu Xin Lin Zhen-Ya Huang Yu Yin Jia-Yu Liu Qi Liu Gang Zhou Anhui Province Key Laboratory of Big Data Analysis and Application School of Data ScienceUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Laboratory of Mathematical Engineering and Advanced Computing Information Engineering UniversityZhengzhou 450001China

Automatically solving math word problems,which involves comprehension,cognition,and reasoning,is a crucial issue in artificial intelligence *** math word problem solvers mainly work on word-level relationship extraction and the generation of expression solutions while lacking consideration of the clause-level *** this end,inspired by the theory of two levels of process in comprehension,we propose a novel clause-level relationship-aware math solver(CLRSolver)to mimic the process of human comprehension from lower level to higher ***,in the lower-level processes,we split problems into clauses according to their natural division and learn their *** the higher-level processes,following human′s multi-view understanding of clause-level relationships,we first apply a CNN-based module to learn the dependency relationships between clauses from word relevance in a local ***,we propose two novel relationship-aware mechanisms to learn dependency relationships from the clause semantics in a global ***,we enhance the representation of clauses based on the learned clause-level dependency *** expression generation,we develop a tree-based decoder to generate the mathematical *** conduct extensive experiments on two datasets,where the results demonstrate the superiority of our framework.

关键词： Artificial intelligence(AI) artificial neural network(ANN) computational mathematics machine intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

Hyperspherical Energy Transformer with Recurrent Depth

arXiv

引用

arXiv 2025年

作者： Hu, Yunzhe Zou, Difan Xu, Dong School of Computing and Data Science The University of Hong Kong Hong Kong

Transformer-based foundation models have achieved unprecedented success with a gigantic amount of parameters and computational resources. Yet, the core building blocks of these models, the Transformer layers, and how they are arranged and configured are primarily engineered from the bottom up and driven by heuristics. For advancing next-generation architectures, it demands exploring a prototypical model that is amenable to high interpretability and of practical competence. To this end, we take a step from the top-down view and design neural networks from an energy minimization perspective. Specifically, to promote isotropic token distribution on the sphere, we formulate a modified Hopfield energy function on the subspace-embedded hypersphere, based on which Transformer layers with symmetric structures are designed as the iterative optimization for the energy function. By integrating layers with the same parameters, we propose Hyper-Spherical Energy Transformer (Hyper-SET), an alternative to the vanilla Transformer with recurrent depth. This design inherently provides greater interpretability and allows for scaling to deeper layers without a significant increase in the number of parameters. We also empirically demonstrate that Hyper-SET achieves comparable or even superior performance on both synthetic and real-world tasks, such as solving Sudoku and masked image modeling, while utilizing fewer parameters. © 2025, CC BY.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Conversational Explanations: Discussing Explainable AI with Non-AI Experts 25

Conversational Explanations: Discussing Explainable AI with ...

引用

30th International Conference on Intelligent User Interfaces, IUI 2025

作者： Zhang, Tong Zhang, Mengao Low, Wei Yan Yang, X. Jessie Li, Boyang Albert College of Computing and Data Science Nanyang Technological University Singapore Singapore Nanyang Technological University Singapore Singapore College of Engineering University of Michigan Ann ArborMI United States

ISBN: (纸本)9798400713064

Explainable AI (XAI) aims to provide insights into the decisions made by AI models. To date, most XAI approaches provide only one-time, static explanations, which cannot cater to users' diverse knowledge levels and information needs. Conversational explanations have been proposed as an effective method to customize XAI explanations. However, building conversational explanation systems is hindered by the scarcity of training data. Training with synthetic data faces two main challenges: lack of data diversity and hallucination in the generated data. To alleviate these issues, we introduce a repetition penalty to promote data diversity and exploit a hallucination detector to filter out untruthful synthetic conversation turns. We conducted both automatic and human evaluations on the proposed system, fEw-shot Multi-round ConvErsational Explanation (EMCEE). For automatic evaluation, EMCEE achieves relative improvements of 81.6% in BLEU and 80.5% in ROUGE compared to the baselines. EMCEE also mitigates the degeneration of data quality caused by training on synthetic data. In human evaluations (N = 60), EMCEE outperforms baseline models and the control group in improving users' comprehension, acceptance, trust, and collaboration with static explanations by large margins. Through a fine-grained analysis of model responses, we further demonstrate that training on self-generated synthetic data improves the model's ability to generate more truthful and understandable answers, leading to better user interactions. To the best of our knowledge, this is the first conversational explanation method that can answer free-form user questions following static explanations. © 2025 Copyright held by the owner/author(s).

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

FluE: A Resource Fluid Equilibrium Strategy for AIGC Within Evolving computing Power Networks

FluE: A Resource Fluid Equilibrium Strategy for AIGC Within ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Liu, Zejun Qiu, Chao Ren, Xiaoxu Wang, Xiaofei Xiong, Zehui Yao, Haipeng Niyato, Dusit Tianjin University College of Intelligence and Computing Tianjin China Beijing University of Posts and Telecommunications School of Information and Communication Engineering Beijing China Singapore University of Technology and Design Singapore Nanyang Technological University College of Computing and Data Science Singapore

ISBN: (纸本)9798350351255

The presence of Artificial Intelligence Generated Content (AIGC) has garnered widespread interest. AIGC enables content creation by analyzing big data, leveraging the capabilities of extensive AI models, and substantial AI computing. computing power networks (CPNs) represent an excellent approach for offering pervasive AI computing resources to AIGC. However, these characteristics have posed unprecedented challenges to the CPNs helped AIGC, including the uncertainty of prompts' information value, the inability to model the continuity of computing resources, and the incapacity to represent complex multi-dimensional spaces. In this paper, we propose a computing resources equilibrium strategy based on the fluid model for AIGC helped by CPNs, namely FluE. This mechanism obtains information entropy by constructing an AIGC prompt tree to measure the information value of AIGC prompts. In addition, we model the continuity of computing resources by the fluid model. A fluid-stopping equilibrium strategy is formulated to obtain the average fluid level of computing resources based on the Laplace-Stieltjes transform. To solve the equilibrium strategy, we develop a diffusion-based algorithm for FluE to adjust the fluid policy dynamically to maximize resource rewards. Finally, the evaluations demonstrate improvements in average social welfare. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Betweenness Centrality on Public Opinion in the 2024 Indonesia Presidential Election Discussion on YouTube

Betweenness Centrality on Public Opinion in the 2024 Indones...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Widha Dwiyanti Putri Rizky Alifiya Muhammad Fauzal Dwiansyah Warih Maharani Data Science School of Computing Telkom University Bandung Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

This research implements betweenness centrality in social media, especially YouTube. This research focuses on analyzing the most influential users in shaping public opinion based on interactions through comments and likes in the YouTube video “Anis vs Prabowo vs Ganjar - Epic Rap Battle of Presidency 2024”. The betweenness centrality method connects various parts of the network, positioning influential nodes as centers. A node has a high betweenness centrality value when the node functions as the main path where other nodes interact. The results of this research showed that the most influential user in shaping public opinion on YouTube video is a User_5670_with 93.00 betweenness centrality value.

关键词： Video on demand Social networking (online) Voting Web sites

来源：评论

学校读者我要写书评

暂无评论

Leveraging Prompt Engineering for Curriculum Design in Short-term Adult Training

Leveraging Prompt Engineering for Curriculum Design in Short...

引用

Educational Technology (ICET), IEEE International Conference on

作者： Hang Wang Ping Chen Ailiya Zhiqi Shen College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350376944

ISBN: (纸本)9798350376951

This paper explores the integration of large language models (LLMs) into the curriculum design process for short-term adult training programs, highlighting the role of prompt engineering as a transformative tool. As adult education needs to adapt rapidly to changing professional landscapes, the ability to quickly develop and customize educational content is paramount. This study introduces a framework that employs prompt engineering to leverage LLMs, such as ChatGPT, for generating customized curriculum design. Through a systematic process, curriculum designers input tailored prompts into LLMs to produce relevant and accurate educational content. The methodology involves iterating these prompts based on feedback to refine and enhance the curriculum. A survey conducted among educational professionals, who have varied familiarity with AI, supports the effectiveness of this approach. The results indicate that well-crafted prompts not only expedites the curriculum development process but may also enhance the educational outcomes by providing more customized and adaptive learning experiences. This approach is posited as a promising solution to the challenges faced in adult education, particularly in settings demanding rapid course development and delivery.

关键词： Training Surveys Accuracy Systematics Large language models Curriculum development Focusing Prompt engineering Fake news Research and development

来源：评论

学校读者我要写书评

暂无评论

RankFIRST: Visual Analysis for Factor Investment By Ranking Stock Timeseries

引用

IEEE Transactions on Visualization and Computer Graphics 2022年 PP卷 1-10页

作者： Guo, Huijie Liu, Meijun Yang, Bowen Sun, Ye Qu, Huamin Shi, Lei SKLSDE and Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University China Hong Kong University of Science and Technology Hong Kong

In the era of quantitative investment, factor-based investing models are widely adopted in the construction of stock portfolios. These models explain the performance of individual stocks by a set of financial factors, e.g., market beta and company size. In industry, open investment platforms allow the online building of factor-based models, yet set a high bar on the engineering expertise of end-users. State-of-the-art visualization systems integrate the whole factor investing pipeline, but do not directly address domain users' core requests on ranking factors and stocks for portfolio construction. The current model lacks explainability, which downgrades its credibility with stock investors. To fill the gap in modeling, ranking, and visualizing stock time series for factor investment, we designed and implemented a visual analytics system, namely RankFIRST. The system offers built-in support for an established factor collection and a cross-sectional regression model viable for human interpretation. A hierarchical slope graph design is introduced according to the desired characteristics of good factors for stock investment. A novel firework chart is also invented extending the well-known candlestick chart for stock time series. We evaluated the system on the full-scale Chinese stock market data in the recent 30 years. Case studies and controlled user evaluation demonstrate the superiority of our system on factor investing, in comparison to both passive investing on stock indices and existing stock market visual analytics tools. IEEE

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

IRS-enabled Wireless Power Transfer and data Collection in UAV-assisted IoT

IRS-enabled Wireless Power Transfer and Data Collection in U...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Xie, Wenwen Sun, Geng Li, Jiahui Wang, Xue Wang, Jiacheng Du, Hongyang Niyato, Dusit Jilin University College of Computer Science and Technology Changchun130012 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Jilin University College of Communication Engineering Changchun130012 China

ISBN: (纸本)9798350351255

An intelligent reflecting surface (IRS)-enabled wireless power transfer (WPT) and data collection scheme for unmanned aerial vehicle (UAV)-assisted Internet of Things (IoT) network is investigated in this paper. Specifically, IoT devices (IoTDs) first harvest energy from the UAV and then upload the sensed data by applying time-division multiple access (TDMA), where an IRS is deployed to improve the transmission quality. We aim to minimize the age of information (AoI) and energy consumption of the UAV. For achieving this, we formulate an optimization problem by jointly optimizing the UAV trajectory, IRS phase shits, charging time allocation, and binary IoTD scheduling, which is a mixed-integer non-convex optimization problem. To address the issue, we first formulate our problem into a Markov decision process (MDP) and then propose an alternating optimization-double parameterized deep Q-network (AO-DPDQN) approach to solve the optimization problem. Specifically, an AO-based method is adopted to optimize the phase shifts of IRS to simplify the action space of MDP, and then double parameterized deep Q-network (DPDQN) is employed to optimize UAV trajectory, charging time allocation, and IoTD scheduling. Simulation results demonstrate the effectiveness and superiority of the proposed approach compared to various baselines. © 2024 IEEE.

关键词： Energy utilization

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：