检索结果-内蒙古大学图书馆

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

作者： Nataly Brukhim Amit Daniely Yishay Mansour Shay Moran Department of Computer Science Princeton University Department of Computer Science Hebrew University Google Research Department of Computer Science Tel Aviv University Google Research Faculty of Mathematics Faculty of Computer Science Faculty of Data and Decision Sciences Technion Google Research

We study a generalization of boosting to the multiclass setting. We introduce a weak learning condition for multiclass classification that captures the original notion of weak learnability as being "slightly better than random guessing". We give a simple and efficient boosting algorithm, that does not require realizability assumptions and its sample and oracle complexity bounds are independent of the number of *** addition, we utilize our new boosting technique in several theoretical applications within the context of List PAC Learning. First, we establish an equivalence to weak PAC learning. Furthermore, we present a new result on boosting for list learners, as well as provide a novel proof for the characterization of multiclass PAC learning and List PAC learning. Notably, our technique gives rise to a simplified analysis, and also implies an improved error bound for large list sizes, compared to previous results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Diffusion Model-Generated Faces by Assessing Smoothness and Noise Tolerance

Detection of Diffusion Model-Generated Faces by Assessing Sm...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Baoping Liu Bo Liu Ming Ding Tianqing Zhu School of Computer Science University of Technology Sydney NSW Australia Data61 CSIRO NSW Australia Faculty of Data Science City University of Macau Macau China

ISBN: (数字)9798350364262

ISBN: (纸本)9798350364279

The fast growth of artificial intelligence (AI) raises much concern about the misinformation brought by AI-generated content (AIGC), especially Deepfake techniques that generate fake human faces. The recent development of Diffusion Models (DMs) moves another critical step forward to generate high-resolution and realistic human faces, which has become a challenge for existing Deepfake detectors. In this paper, we propose a DM-generated image detector by looking into the generation pipeline of DMs and the details of DM-generated images. The detector is based on the observation that DM-generated human faces show over-smooth textures and do not contain details as real human faces. Through a comprehensive analysis of DM-generated faces in spatial and frequency domains, we noticed that the over-smoothness improves the tolerance of Gaussian noise since excessive smoothness mitigates some of the impact of noise. Inspired by the observations, we propose a Deepfake detector capable of recognizing challenging DM-generated faces. We mainly propose the Noise Residual Unit (NRD) in our framework to collect the frequency response of images to Gaussian noise as distinctive features for classification. In detail, for an input face image, we add Gaussian noise to it and get the noise-degraded image. Then, the NRU generates the Noise Residual Image (NRI) by calculating the residual of the high-pass-filtered original image and the high-pass-filtered degraded image. The NRI indicates the high-frequency impact brought by the Gaussian noise and, therefore, suggests the tolerance of the original image to noise degradation. The original image and NRI are encoded and fused to obtain the joint representation, which is then fed to a classifier to predict the binary label. We conducted comprehensive experiments to evaluate the effectiveness of the proposed detector. The results indicate that our proposed detector achieves state-of-the-art detection performance on DM-generated faces and generali

关键词： Deepfakes Analytical models Gaussian noise Frequency-domain analysis Pipelines Detectors Frequency response

来源：评论

学校读者我要写书评

暂无评论

Explainable AI in Handwriting Detection for Dyslexia Using Transfer Learning

arXiv

引用

arXiv 2024年

作者： Robaa, Mahmoud Balat, Mazen Awaad, Rewaa Omar, Esraa Aly, Salah A. CS & IT Dept. Egypt-Japanese University of Science & Tech. Alexandria Egypt Computer Science Faculty of Science Fayoum University Fayoum Egypt Faculty of Computing & Data Science Badya University Giza Egypt

This study introduces an explainable AI (XAI) framework for the detection of dyslexia through handwriting analysis, achieving an impressive test precision of 99.65%. The framework integrates transfer learning and transformer-based models, identifying handwriting features associated with dyslexia while ensuring transparency in decision-making via Grad-CAM visualizations. Its adaptability to different languages and writing systems underscores its potential for global applicability. By surpassing the classification accuracy of state-of-the-art methods, this approach demonstrates the reliability of handwriting analysis as a diagnostic tool. The findings emphasize the framework’s ability to support early detection, build stakeholder trust, and enable personalized educational strategies. © 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

A Vision-Based Autonomous AI Tic-Tac-Toe Manipulation System 12

A Vision-Based Autonomous AI Tic-Tac-Toe Manipulation System

引用

12th International Electrical Engineering Congress, iEECON 2024

作者： Rakprayoon, Panjawee Ounsiri, Akechai Chongyoa, Ratchanon Bangkok University Faculty Of Engineering Dept. Ai Engineering And Data Science Pathum Thani Thailand Dna Robotics And Automation System Company Limited Pathum Thani Thailand Bangkok University Faculty Of Engineering Dept. Computer And Robotics Engineering Pathum Thani Thailand

ISBN: (纸本)9798350383591

For an AI tic-tac-toe manipulator application, a real-time vision-based approach is proposed. The technique employs the RealSense camera to capture color and depth images. Combining object detection and image processing techniques to identify X's and O's positions on the game board. However, we recognize that errors can occur during object movement when using only 2D images. To solve this problem, a calibration method between RealSense and the manipulator based on the point-to-plane ICP algorithm is presented. This method provides the 3D object position in the robot coordinate, resulting in increasing the accuracy from 86.25% to 97.25%. Our experiment shows that this technique is highly effective and can accurately identify position objects. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Efficient Model based on Machine Learning Algorithms for Virtual Machines Classification in Cloud Computing Environment 4

An Efficient Model based on Machine Learning Algorithms for ...

引用

4th International Conference on Innovative Research in Applied science, Engineering and Technology, IRASET 2024

作者： Amahrouch, Abdelhadi Bouhamidi, Mehdi Saadi, Youssef El Kafhali, Said Sultan Moulay Slimane University Faculty Of Sciences And Techniques Data Science For Sustainable Earth Laboratory B.P. 523 Beni Mellal23000 Morocco Polytechnic University Laboratory Of Industrial And Human Automation Mechanics And Computer Science Hauts-de-France France Hassan First University Of Settat Faculty Of Sciences And Techniques Computer Networks Modeling And Mobility Laboratory B.P. 539 Settat26000 Morocco

ISBN: (纸本)9798350309508

In cloud computing, virtual machines consolidation (VMC) techniques are commonly used to improve resource utilization and reduce energy consumption. Task scheduling in cloud systems is a crucial aspect of VMC as it involves mapping clients' requirements to the appropriate computing resources such as Virtual Machines (VMs) or Physical Machines (PMs). The cloud provider must ensure that tasks are executed efficiently using the available shared computing resources while maintaining the quality of service (QoS) and minimizing the carbon footprint. Therefore, a good VM migration based on the customer's needs and IT resource capacity is required to maintain the best performance of the cloud system. In this work, we introduce an approach that leverage machine learning-based algorithms for VMs classification based on their latency sensitivity to facilitate subsequent migration into a suitable PM for better VMC. These algorithms categorize VMs into two groups: potentially inter-active machines (exhibiting periodic behavior on a daily scale) and latency-insensitive machines (for example, batch workloads, development, and test workloads). Our model demonstrated robust performance, achieving an accuracy of around 83%, thus establishing itself as the most proficient classifier in this study. © 2024 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Granular-Ball Computing Based Fuzzy Twin Support Vector Machine for Pattern Classification

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Lang, Guangming Zhao, Lixi Miao, Duoqian Ding, Weiping Changsha University of Science and Technology School of Mathematics and Statistics Changsha410114 China Tongji University School of Computer Science and Technology Shanghai201804 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

The twin support vector machine (TWSVM) classifier and its fuzzy variant (FTSVM) have received considerable attention due to their low computational complexity. However, their performance often deteriorates when the input data is affected by noise. To overcome this limitation, this study leverages the robustness of granular-ball computing (GBC) against noise to develop more effective classification models by integrating GBC with TWSVM and FTSVM. First, we introduce the granular-ball twin support vector machine (GBTWSVM) classifier, which incorporates GBC with the TWSVM framework. By replacing traditional point-wise inputs with granular-ball representations, we derive a pair of non-parallel hyperplanes for the GBTWSVM classifier by solving a quadratic programming problem. Afterwards, we develop the granular-ball fuzzy twin support vector machine (GBFTSVM) classifier, where the membership and non-membership functions of granular-balls are defined using Pythagorean fuzzy sets (PFS), enabling a more nuanced differentiation of the contributions of granular-balls from distinct regions within the input space. By incorporating these functions into the FTSVM framework, we derive a pair of non-parallel hyperplanes for the GBFTSVM classifier through the solution of a quadratic programming problem. Finally, we present algorithms for the GBTWSVM and GBFTSVM classifiers and evaluate their performance on 21 benchmark datasets. Experimental results demonstrate the superior scalability, computational efficiency, and robustness of the proposed classifiers in pattern recognition, highlighting their potential as advanced tools for noise-tolerant classification. © 1993-2012 IEEE.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

A Trichotomy for Transductive Online Learning

arXiv

引用

arXiv 2023年

作者： Hanneke, Steve Moran, Shay Shafer, Jonathan Department of Computer Science Purdue University United States Faculty of Mathematics Faculty of Computer Science Faculty of Data and Decision Sciences Technion Israel Institute of Technology Computer Science Division UC Berkeley United States

We present new upper and lower bounds on the number of learner mistakes in the ‘transductive’ online learning setting of Ben-David, Kushilevitz and Mansour (1997). This setting is similar to standard online learning, except that the adversary fixes a sequence of instances x1, . . ., xn to be labeled at the start of the game, and this sequence is known to the learner. Qualitatively, we prove a trichotomy, stating that the minimal number of mistakes made by the learner as n grows can take only one of precisely three possible values: n, Θ (log(n)), or Θ(1). Furthermore, this behavior is determined by a combination of the VC dimension and the Littlestone dimension. Quantitatively, we show a variety of bounds relating the number of mistakes to well-known combinatorial dimensions. In particular, we improve the known lower bound on the constant in the Θ(1) case from Ω (plog(d) ) to Ω(log(d)) where d is the Littlestone dimension. Finally, we extend our results to cover multiclass classification and the agnostic setting. © 2023, CC BY.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

PROMPTING LABEL EFFICIENCY IN FEDERATED GRAPH LEARNING VIA PERSONALIZED SEMI-SUPERVISION 49

PROMPTING LABEL EFFICIENCY IN FEDERATED GRAPH LEARNING VIA P...

引用

2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024

作者： Mao, Qinghua Lin, Xi Su, Xiu Li, Gaolei Chen, Lixing Li, Jianhua Shanghai Jiao Tong University China Big Data Institute Central South University China School of Computer Science Faculty of Engineering The University of Sydney Australia Shanghai Key Laboratory of Integrated Administration Technologies for Information Security China

ISBN: (纸本)9798350344851

Federated graph learning (FGL) enables the collaborative training of graph neural networks (GNNs) in a distributed manner. A critical challenge in FGL is label deficiency, which becomes more intricate due to non-IID decentralized data. Existing methods have focused on extracting knowledge from abundant unlabeled data, leaving few-shot labeled data unexplored. To this end, we propose ConFGL, a novel FGL framework to enhance label efficiency in federated learning with non-IID subgraphs. We formulate a semi-supervised objective to harness both unlabeled and labeled data, where self-supervised learning is achieved via a graph contrastive module. Additionally, a personalized federated learning (FL) strategy is adopted to concurrently train a global model and an individual model, which helps alleviate the representation disparities encoded by local models. Extensive experiments on four node-level datasets under non-IID settings have shown that ConFGL can consistently provide an average of 4.10% accuracy gains over supervised FL personalization methods while maintaining a higher GPU throughput. © 2024 IEEE

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Assessing the Ability of AI-Driven Natural Language Processing to Accurately Analyze Unstructured Text data 3

Assessing the Ability of AI-Driven Natural Language Processi...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Vigenesh, M. RaviKumar, V. Patil, Vivek D. Kumar, Sharma Sonu Geyi, Nyarik Chattopadhyay, Subir Karpagam Academy of Higher Education Department of Computer Science Engineering Coimbatore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Mangalayatan University Department of Computer Science Aligarh India Himalayan University Department of Bussiness & Management Itanagar India Usha Martin University Faculty of Business Mangagement & Commerce Ranchi India

ISBN: (纸本)9798350319125

This technical abstract examines the ability of herbal language processing (NLP)-driven synthetic Intelligence (AI) to analyze unstructured textual content facts. Unstructured textual content records include information from assets with webpages, social media, emails, and consumer comments. They are widely used in sentiment evaluation, hazard detection, and entity extraction programs. NLP-pushed AI answers along with natural language knowledge (NLU), herbal language knowledge (NLG), and natural language understanding (NLP) are used to manner and examine unstructured textual content information. The analysis technique starts evolving with tokenizing the facts, breaking the textual content into smaller factors, including phrases and phrases. After tokenizing the statistics, the AI device discovers styles inside the records. Those styles can then discover the emotions and entities inside the data. NLU and NLG models are used to expand the facts' expertise by assigning sentiment and issue-level scores. The accuracy of NLP-driven AI is similarly progressed through more excellent complex fashions consisting of deep studying and reinforcement. © 2023 IEEE.

关键词： extraction phrases statistics tokenized webpages

来源：评论

学校读者我要写书评

暂无评论

Low-Resource Named Entity Recognition: Can One-vs-All AUC Maximization Help? 23

Low-Resource Named Entity Recognition: Can One-vs-All AUC Ma...

引用

23rd IEEE International Conference on data Mining, ICDM 2023

作者： Nguyen, Ngoc Dang Tan, Wei Du, Lan Buntine, Wray Beare, Richard Chen, Changyou Monash University Department of Data Science and Ai Melbourne Australia VinUniversity College of Engineering and Computer Science Hanoi Viet Nam Faculty of Medicine Peninsula Clinical School Melbourne Australia University at Buffalo Department of Cs and Engineering New York United States

ISBN: (纸本)9798350307887

Named entity recognition (NER), a task that identifies and categorizes named entities such as persons or organizations from text, is traditionally framed as a multi-class classification problem. However, this approach often overlooks the issues of imbalanced label distributions, particularly in low-resource settings, which is common in certain NER contexts, like biomedical NER (bioNER). To address these issues, we propose an innovative reformulation of the multi-class problem as a one-vs-all (OVA) learning problem and introduce a loss function based on the area under the receiver operating characteristic curve (AUC). To enhance the efficiency of our OVA-based approach, we propose two training strategies: one groups labels with similar linguistic characteristics, and another employs meta-learning. The superiority of our approach is confirmed by its performance, which surpasses traditional NER learning in varying NER settings. © 2023 IEEE.

关键词： Natural language processing systems

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：