检索结果-内蒙古大学图书馆

International Symposium on Networks, computers and Communications (ISNCC)

作者： Khaoula ElBedoui Computer Science Departement at ENICarthage Carthage University Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) LR16ES06 Laboratoire de recherche en Informatique Modélisation et Traitement de l'Information et de la Connaissance (LIMTIC) Institut Supérieur d'Informatique - Université de Tunis El Manar Tunis Tunisia

In this paper, we present a new approach for ECG signal classification based on Federated Unlearning (FUL) concept. In fact, the analysis and the processing of ECG signals are a key element in the diagnosis of cardiovascular diseases. Consequently, the ECG classification is an important task that must be performed efficiently. In this context, the use of machine learning (ML) approaches, and in particular deep learning (DL) models is interesting since they are increasingly enabling accurate and rapid classification. Moreover, the sample-related problems that are often encountered by these models (poor quality or limited quantity) can be solved through mainly the pre-processing steps. But only one problem remains to be solved “Access to medical data”. This latter is often limited because of strict regulations on patient data confidentiality and the dispersal of these data across different healthcare institutions (hospitals, clinics, or research centers). So, data collection for learning is not usually possible, but it is subject to ethical/legal constraints. To overcome this problem, the Federated Learning (FL) seems to be a solution since it is a way to train a shared DL model on decentralized data. This improves diagnosis while preserving patient privacy. However, the data owner (patient) has usually the right to ask the institution that is keeping his/her data to delete it under the Right to be Forgotten. This post-process operation of FL is the “federated unlearning” which implies that, in addition to the data itself, any impact that the data may have on the FL model must be removed. So, in this paper, we present the first use of FUL for ECG classification. The evaluation of this model on three datasets confirms its efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS

arXiv

引用

arXiv 2020年

作者： Yu, Kaicheng Ranftl, Rene Salzmann, Mathieu Computer vision lab EPFL Swiss National Science Foundation Intelligent Systems Lab Intel.

Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design and train the shared-weight backbone network, a.k.a. the super-net. Since heuristics and hyperparameters substantially vary across different methods, a fair comparison between them can only be achieved by systematically analyzing the influence of these factors. In this paper, we therefore provide a systematic evaluation of the heuristics and hyperparameters that are frequently employed by weight-sharing NAS algorithms. Our analysis uncovers that some commonly-used heuristics for super-net training negatively impact the correlation between super-net and stand-alone performance, and evidences the strong influence of certain hyperparameters and architectural choices. Our code and experiments set a strong and reproducible baseline that future works can build on. Copyright © 2020, The Authors. All rights reserved.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

Measuring Acoustics with Collaborative Multiple Agents

arXiv

引用

arXiv 2023年

作者： Yu, Yinfeng Chen, Changan Cao, Lele Yang, Fangkai Sun, Fuchun Beijing National Research Center for Information Science and Technology State Key Lab on Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University China University of Texas Austin United States Motherbrain EQT Group Microsoft Research United States THU-Bosch JCML Center China College of Information Science and Engineering Xinjiang University China

As humans, we hear sound every second of our life. The sound we hear is often affected by the acoustics of the environment surrounding us. For example, a spacious hall leads to more reverberation. Room Impulse Responses (RIR) are commonly used to characterize environment acoustics as a function of the scene geometry, materials, and source/receiver locations. Traditionally, RIRs are measured by setting up a loudspeaker and microphone in the environment for all source/receiver locations, which is time-consuming and inefficient. We propose to let two robots measure the environment's acoustics by actively moving and emitting/receiving sweep signals. We also devise a collaborative multi-agent policy where these two robots are trained to explore the environment's acoustics while being rewarded for wide exploration and accurate prediction. We show that the robots learn to collaborate and move to explore environment acoustics while minimizing the prediction error. To the best of our knowledge, we present the very first problem formulation and solution to the task of collaborative environment acoustics measurements with multiple agents. © 2023, CC BY-NC-ND.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

HCIlab at Memotion 2.0 2022: Analysis of Sentiment, Emotion and Intensity of Emotion Classes from Meme Images using Single and Multi Modalities 1

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion ...

引用

1st Workshop on Multimodal Fact-Checking and Hate Speech Detection, DE-FACTIFY 2022

作者： Nguyen, Thanh Tin Pham, Nhat Truong Nguyen, Ngoc Duy Nguyen, Hai Nguyen, Long H. Kim, Yong-Guk Human Computer Interaction Lab Department of Computer Engineering Sejong University Seoul Korea Republic of Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Institute for Intelligent Systems Research and Innovation Deakin University Victoria Australia Khoury College of Computer Sciences Northeastern University Boston United States Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam

Nowadays, memes found on internet are overwhelming. Although they are innocuous and sometimes entertaining, there exist memes that contain sarcasm, offensive, or motivational feelings. In this study, several approaches are proposed to solve the multiple modality problem in analysing the given meme dataset. The imbalance issue has been addressed by using a new Auto Augmentation method and the uncorrelation issue has been mitigated by adopting deep Canonical Correlation Analysis to find the most correlated projections of visual and textual feature embedding. In addition, both stacked attention and multi-hop attention network are employed to efficiently generate aggregated features. As a result, our team, i.e. HCIlab, achieved a weighted F1 score of 0.4995 for sentiment analysis, 0.7414 for emotion classification, and 0.5301 for scale/intensity of emotion classes on the leaderboard. This results are obtained by using concatenation between image and text model and our code can be found at https://***/JMRa8. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Many-Class Text Classification with Matching

arXiv

引用

arXiv 2022年

作者： Song, Yi Gu, Yuxian Huang, Minlie The CoAI group Tsinghua University Beijing China Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China

In this work, we formulate Text Classification as a Matching problem between the text and the labels, and propose a simple yet effective framework named TCM. Compared with previous text classification approaches, TCM takes advantage of the fine-grained semantic information of the classification labels, which helps distinguish each class better when the class number is large, especially in low-resource scenarios. TCM is also easy to implement and is compatible with various large pretrained language models. We evaluate TCM on 4 text classification datasets (each with 20+ labels) in both few-shot and full-data settings, and this model demonstrates significant improvements over other text classification paradigms. We also conduct extensive experiments with different variants of TCM and discuss the underlying factors of its success. Our method and analyses offer a new perspective on text classification. © 2022, CC BY.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Two-Limbed 3T1R Haptic Device

Design and Implementation of a Two-Limbed 3T1R Haptic Device

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Long Kang Yang Yang Byung-Ju Yi PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Xi'an Modern Control Technology Research Institute Xi'an China School of Automation Nanjing University of Information Science and Technology Nanjing China Department of the Electronic Systems Engineering Hanyang University Ansan South Korea

This paper presents a haptic device with a simple architecture of only two limbs that can provide translational motion in three degrees of freedom (DOF) and one-DOF rotational motion. Actuation redundancy eliminates all forward-kinematic singularities and improves the motion-force transmission property. Thanks to the special structure of the kinematic chains, all actuators are close to the base and full gravity compensation is achieved passively by using springs. Force producibility analysis shows that this haptic device is able to produce long-term continuous force feedback of 15–30 N in each direction. By developing a prototype of the haptic device and a virtual three-dimensional simulator, a preliminary performance evaluation of the haptic device was conducted. In addition, a torque distribution algorithm considering a relaxed form of actuator-torque saturation was experimentally evaluated, and a comparison with other algorithms reveals that this algorithm offers several advantages.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization

arXiv

引用

arXiv 2022年

作者： Gu, Yuxian Ke, Pei Zhu, Xiaoyan Huang, Minlie The CoAI group Tsinghua University Beijing China Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China

Training language models to learn from human instructions for zero-shot cross-task generalization has attracted much attention in NLP communities. Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on a massive collection of tasks described via human-craft instructions, has been shown effective in instruction learning for unseen tasks. However, IT relies on a large amount of human-annotated samples, which restricts its generalization. Unlike labeled data, unlabeled data are often massive and cheap to obtain. In this work, we study how IT can be improved with unlabeled data. We first empirically explore the IT performance trends versus the number of labeled data, instructions, and training tasks. We find it critical to enlarge the number of training instructions, and the instructions can be underutilized due to the scarcity of labeled data. Then, we propose Unlabeled Data Augmented Instruction Tuning (UDIT) to take better advantage of the instructions during IT by constructing pseudo-labeled data from unlabeled plain texts. We conduct extensive experiments to show UDIT’s effectiveness in various scenarios of tasks and datasets. We also comprehensively analyze the key factors of UDIT to investigate how to better improve IT with unlabeled data. © 2022, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A circuit-generated quantum subspace algorithm for the variational quantum eigensolver

arXiv

引用

arXiv 2024年

作者： Hirsbrunner, Mark R. Mullinax, J. Wayne Shen, Yizhi Williams-Young, David B. Klymko, Katherine Van Beeumen, Roel Tubman, Norm M. Department of Physics University of Illinois at Urbana-Champaign UrbanaIL61801 United States USRA Research Institute for Advanced Computer Science Mountain ViewCA94043 United States KBR Inc. NASA Ames Research Center Moffett FieldCA94035 United States Intelligent Systems Division NASA Ames Research Center Moffett FieldCA94035 United States Applied Mathematics and Computational Research Division Lawrence Berkeley National Lab BerkeleyCA94720 United States NERSC Lawrence Berkeley National Lab BerkeleyCA94720 United States

Recent research has shown that wavefunction evolution in real- and imaginary-time can generate quantum subspaces with significant utility for obtaining accurate ground state energies. Inspired by these methods, we propose combining quantum subspace techniques with the variational quantum eigensolver (VQE). In our approach, the parameterized quantum circuit is divided into a series of smaller subcircuits. The sequential application of these subcircuits to an initial state generates a set of wavefunctions that we use as a quantum subspace to obtain high-accuracy groundstate energies. We call this technique the circuit subspace variational quantum eigensolver (CSVQE) algorithm. By benchmarking CSVQE on a range of quantum chemistry problems, we show that it can achieve significant error reduction in the best case compared to conventional VQE, particularly for poorly optimized circuits, greatly improving convergence rates. Furthermore, we demonstrate that when applied to circuits trapped at a local minima, CSVQE can produce energies close to the global minimum of the energy landscape, making it a potentially powerful tool for diagnosing local minima. © 2024, CC BY-NC-SA.

关键词： Ground state

来源：评论

学校读者我要写书评

暂无评论

FEDCSD: A FEDERATED LEARNING BASED APPROACH FOR CODE-SMELL DETECTION

arXiv

引用

arXiv 2023年

作者： Alawadi, Sadi Alkharabsheh, Khalid Alkhabbas, Fahed Kebande, Victor Awaysheh, Feras M. Palomba, Fabio Awad, Mohammed Center for Applied Intelligent Systems Research School of Information Technology Halmstad University Halmstad Sweden Department of Software Engineering Prince Abdullah bin Ghazi Faculty of Information and Communication Technology Al-Balqa Applied University Jordan Internet of Things and People Research Center Malmö University Sweden Department of Computer Science Blekinge Institute of Technology Sweden Institute of Computer Science Delta Research Centre University of Tartu Estonia SeSa Lab University of Salerno Italy Arab American University Palestine Palestine

Software quality is critical, as low quality, or "Code smell," increases technical debt and maintenance costs. There is a timely need for a collaborative model that detects and manages code smells by learning from diverse and distributed data sources while respecting privacy and providing a scalable solution for continuously integrating new patterns and practices in code quality management. However, the current literature is still missing such capabilities. This paper addresses the previous challenges by proposing a Federated Learning Code Smell Detection (FedCSD) approach, specifically targeting "God Class," to enable organizations to train distributed ML models while safeguarding data privacy collaboratively. We conduct experiments using manually validated datasets to detect and analyze code smell scenarios to validate our approach. Experiment 1, a centralized training experiment, revealed varying accuracies across datasets, with dataset two achieving the lowest accuracy (92.30%) and datasets one and three achieving the highest (98.90% and 99.5%, respectively). Experiment 2, focusing on cross-evaluation, showed a significant drop in accuracy (lowest: 63.80%) when fewer smells were present in the training dataset, reflecting technical debt. Experiment 3 involved splitting the dataset across 10 companies, resulting in a global model accuracy of 98.34%, comparable to the centralized model’s highest accuracy. The application of federated ML techniques demonstrates promising performance improvements in code-smell detection, benefiting both software developers and researchers. Copyright © 2023, The Authors. All rights reserved.

关键词： computer software selection and evaluation

来源：评论

学校读者我要写书评

暂无评论

Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models

arXiv

引用

arXiv 2024年

作者： Sun, Wangtao Zhang, Chenxiang Zhang, Xueyou Yu, Xuanqing Huang, Ziyang Xu, Haotian Chen, Pei He, Shizhu Zhao, Jun Liu, Kang The Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China CAS Engineering Laboratory for Intelligent Industrial Vision Institute of Automation Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering Texas A&M University United States Shanghai Artificial Intelligence Laboratory China Xiaohongshu Inc China AI Lab AIGility Cloud Innovation Beijing China

Although Large Language Models (LLMs) have demonstrated strong instruction-following ability, they are further supposed to be controlled and guided by inferential rules in real-world scenarios to be safe, accurate, and intelligent. This demands the possession of inferential rule-following capability of LLMs. However, no prior work has made a clear evaluation of the inferential rule-following capability of LLMs. Previous studies that try to evaluate the inferential rule-following capability of LLMs fail to distinguish the inferential rule-following scenarios from the instruction-following scenarios. Therefore, this paper first clarifies the concept of inferential rule-following and proposes a comprehensive benchmark, RuleBench, to evaluate a diversified range of inferential rule-following abilities. Our experimental results on a variety of LLMs show that they are still limited in following rules. Our analysis based on the evaluation results provides insights into the improvements for LLMs toward a better inferential rule-following intelligent agent. We further propose Inferential Rule-Following Tuning (IRFT). The experimental results show that through IRFT, LLMs can learn abstract inferential rule-following abilities from purely synthetic data and then generalize to RuleBench. The data and code can be found at: https://***/r/llm-rulefollowing-B3E3/ Copyright © 2024, The Authors. All rights reserved.

关键词： intelligent agents

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：