检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Chu, Yifeng Raginsky, Maxim Department of Electrical and Computer Engineering and Coordinated Science Laboratory University of Illinois UrbanaIL61801 United States

ISBN: (纸本)9781713899921

This paper presents a general methodology for deriving information-theoretic generalization bounds for learning algorithms. The main technical tool is a probabilistic decorrelation lemma based on a change of measure and a relaxation of Young's inequality in Lψp Orlicz spaces. Using the decorrelation lemma in combination with other techniques, such as symmetrization, couplings, and chaining in the space of probability measures, we obtain new upper bounds on the generalization error, both in expectation and in high probability, and recover as special cases many of the existing generalization bounds, including the ones based on mutual information, conditional mutual information, stochastic chaining, and PAC-Bayes inequalities. In addition, the Fernique-Talagrand upper bound on the expected supremum of a subgaussian process emerges as a special case. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Study between Global and Local Explainable Models 14

Comparative Study between Global and Local Explainable Model...

引用

14th International Conference on Intelligent Systems: Theories and Applications, SITA 2023

作者： Dafali, Sidi Mohamed Kissi, Mohamed El Beggar, Omar University Hassan Ii Casablanca Laboratory Lim Department of Computer Science Faculty of Sciences and Techniques Mohammedia Morocco

ISBN: (纸本)9798350308211

Despite opaque machine learning models outperform transparent models, users are still unable to comprehend and trust their ***, Explainable Artificial Intelligence (XAI) becomes a prominent research area. The main objective of this discipline is providing new techniques, tools and models that explain how opaque machine learning models operate to give predictions or simply offer some information about system *** this article, we present an experimental evaluation of explainable models used in XAI, namely: LIME, SHAP, ANCHOR and EBM. Those models are applied on the results of two opaque machine learning models: Random Forest and XGBoost. Our experimental evaluation covers various aspects for comparison including:•Examining the explainability coverage of methods.•Comparing explanations provided by each method. © 2023 IEEE.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

Impact of Stress During COVID-19 Pandemic 9

Impact of Stress During COVID-19 Pandemic

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Angalakuditi, Hindu Bhowmik, Biswajit National Institute of Technology Karnataka BRICS Laboratory Department of Computer Science and Engineering Surathkal Mangalore575025 India

ISBN: (纸本)9798350397376

The COVID-19 pandemic has affected our lives in many ways. Many people faced different challenges during the pandemic to accomplish their daily activities. Many people faced various challenges during the pandemic might have been very stressful, overwhelming, and disgusting. Therefore, it is common to feel stress, irritation, mood swings, and anxiety during the pandemic. Different methodologies by medical practitioners are being taken. Additionally, researchers from academia are also trying to strengthen the methods. Unfortunately, the way for automatic, continuous, and invisible stress detection by the researchers are insufficient and not studied in depth. It becomes essential in the post-pandemic scenario due to COVID-19 disease. This paper studies the impact of stress on people during the COVID-19 pandemic. The study includes origin, classification, impact on health, prevention solutions, etc. Further statistics on the affected people by the stress during the period are provided. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Grey-box Adversarial Attack on Communication in Multi-agent Reinforcement Learning 22

Grey-box Adversarial Attack on Communication in Multi-agent ...

引用

22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023

作者： Ma, Xiao Li, Wu-Jun National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Although research on communication in multi-agent reinforcement learning (MARL) has achieved some progress, the vulnerability of the communication mechanism in MARL caused by adversarial communication messages generated by malicious agents has not been well investigated. Existing works about adversarial communication messages in MARL focus on the black-box scenario where the attacker cannot access any model information about the multi-agent system (MAS). But a more practical setting is the grey-box scenario where the attacker can access the model information about its controlled agent. To the best of our knowledge, there has not been any work investigating grey-box attacks on communication in MARL. In this paper, we propose the first grey-box attack method on communication in MARL, which is called victim-simulation based adversarial attack (VSA). At each timestep, the attacker simulates a victim attacked by other regular agents' communication messages and generates adversarial perturbations on its received communication messages. The aggregation of these perturbations is sent by the attacker to the regular agents through communication messages, which will induce non-optimal actions of the regular agents. Experimental results show that VSA can effectively degrade the performance of the MAS on Predator-Prey. The findings in this paper will make researchers aware of the grey-box attack in MARL. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Benchmark and Scoring Algorithm for Enriching Arabic Synonyms 12

A Benchmark and Scoring Algorithm for Enriching Arabic Synon...

引用

12th Global Wordnet Conference, GWC 2023

作者： Ghanem, Sana Jarrar, Mustafa Jarrar, Radi Bounhas, Ibrahim Department of Computer Science Birzeit University Palestine Palestine LISI Laboratory of Computer Science for Industrial System INSAT Carthage University Tunisia JARIR Joint group for Artificial Reasoning and Information Retrieval Tunisia

ISBN: (纸本)9781713890881

This paper addresses the task of extending a given synset with additional synonyms taking into account synonymy strength as a fuzzy value. Given a mono/multilingual synset and a threshold (a fuzzy value [0 − 1]), our goal is to extract new synonyms above this threshold from existing lexicons. We present twofold contributions: an algorithm and a benchmark dataset. The dataset consists of 3K candidate synonyms for 500 synsets. Each candidate synonym is annotated with a fuzzy value by four linguists. The dataset is important for (i) understanding how much linguists (dis/)agree on synonymy, in addition to (ii) using the dataset as a baseline to evaluate our algorithm. Our proposed algorithm extracts synonyms from existing lexicons and computes a fuzzy value for each candidate. Our evaluations show that the algorithm behaves like a linguist and its fuzzy values are close to those proposed by linguists (using RMSE and MAE). The dataset and a demo page are publicly available at https://***/synonyms. © 2023 12th Global Wordnet Conference, GWC 2023. All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Vision- and Grating-Sensor-Based Intelligent Unmanned Settlement System

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 254-264页

作者： Zhang, Hong-Bo Zhou, Yi-Zhong Dong, Li-Jia Lei, Qing Du, Ji-Xiang Department of Computer Science and Technology Huaqiao University Xiamen361000 China Xiamen Key Laboratory of Computer Vision and Pattern Recognition The Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen361000 China

In this article, a new vision- and grating-sensor-based intelligent unmanned settlement (IUS) system is proposed for convenience stores to automatically recognize the shopping behavior of customers, record their identities, and generate invoices. First, we design a new IUS architecture, which includes a shelf module and exit module. To achieve automatic settlement for each customer, a shopping event detection method is proposed. In this method, a vision-based human pose estimation algorithm is used to detect a human form standing in front of a shelf. The hand actions of each customer are detected by a grating sensor, and an image recognition method based on a convolutional neural network (CNN) is applied to recognize the items in the hands of customers. To reduce the image annotation workload, we propose a semisupervised training method for the recognition network. Based on hand action detection and item recognition, a shopping event recognition method is designed for the system, and a facial image of the customer corresponding to each shopping behavior is captured. Finally, each detected shopping event is added to the invoice of the corresponding customer via a facial recognition method. To verify the effectiveness of the proposed IUS system, we have built a handheld item image dataset and a shopping event dataset for an unmanned convenience store. The experimental results show that the proposed system can accurately recognize shopping behaviors and generate invoices. © 2020 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Improving plant disease classification using realistic data augmentation

引用

Multimedia Tools and Applications 2024年第38期83卷 86141-86160页

作者： Benabbas, Wassim Brahimi, Mohammed Akhrouf, Samir Fortas, Bilal Department of Computer Science Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj Algeria Algiers Algeria Laboratory of Physical Chemistry and Biological Materials Skikda Algeria Laboratory of Informatics and its Applications Mohamed Boudiaf University M’Sila Algeria Department of Computer Science Mohamed Boudiaf University M’Sila Algeria Department of agronomics sciences Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj Algeria Sétif Algeria

Recently, several studies have used deep convolutional neural networks (DCNN) for plant disease classification based on leaf symptoms images. Most of these studies use the PlantVillage dataset, which contains simple images with simple backgrounds. This has led to classifiers achieving high accuracy in academic settings but underperforming in practical scenarios where images taken by farmers are much more complex. In this paper, we propose a data augmentation (DA) method that transforms simple images from the PlantVillage dataset into more complex images, thereby bridging the gap between academic results and practical performance. Our technique focuses on making the images more realistic by generating images containing multiple leaves and complex backgrounds, such as soil. To evaluate the impact of our proposed method, we trained DCNN models using various augmentation methods and tested them on a dataset containing highly complex images comparable to those taken by farmers, posing a substantial challenge. The experimental results showed that models trained on images generated by our method outperformed traditional data augmentation methods, such as geometric transformations. Moreover, our method is competitive with Generative Adversarial Networks (GANs) without requiring any training phase. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Low-code/No-code Development : A systematic literature review 14

Low-code/No-code Development : A systematic literature revie...

引用

14th International Conference on Intelligent Systems: Theories and Applications, SITA 2023

作者： El Kamouchi, Hind Kissi, Mohamed El Beggar, Omar University Hassan Ii Casablanca Laboratory Lim Department of Computer Science Faculty of Sciences and Techniques Mohammedia Morocco

ISBN: (纸本)9798350308211

The emerging trend of Low-code/No-code development has garnered significant attention from both the business and academic communities. This article provides a systematic literature review that explores the different aspects of Low-code/No-code development. The review focuses on gathering state-of-the-art research, methodologies, and frameworks in this field. It also identifies key challenges and benefits associated with Low-code/No-code development. This review aims to provide a comprehensive understanding of the current trends and advancements in this kind of software engineering. This study could serve as a valuable resource for researchers, practitioners, and organizations looking to adopt Low-code/No-code approaches. Overall, this review contributes to the existing body of knowledge by providing insightful findings and suggestions for future research directions in the Low-code/No-code development realm. © 2023 IEEE.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Fairness Auditing, Explanation and Debiasing in Linguistic Data and Language Models 1

Fairness Auditing, Explanation and Debiasing in Linguistic D...

引用

Joint 1st World Conference on eXplainable Artificial Intelligence: Late-Breaking Work, Demos and Doctoral Consortium, xAI-2023: LB-D-DC

作者： Manerba, Marta Marchiori Computer Science Department University of Pisa Italy KDD Laboratory ISTI National Research Council Pisa Italy

This research proposal is framed in the interdisciplinary exploration of the socio-cultural implications that AI exerts on individual and groups. The focus concerns contexts where models can amplify discriminations through algorithmic biases, e.g., in recommendation and ranking systems or abusive language detection classifiers, and the debiasing of their automated decisions to become beneficial and just for everyone. To address these issues, the main objective of the proposed research project is to develop a framework to perform fairness auditing and debiasing of both classifiers and datasets, starting with, but not limited to, abusive language detection, thus broadening the approach toward other NLP tasks. Ultimately, by questioning the effectiveness of adjusting and debiasing existing resources, the project aims at developing truly inclusive, fair, and explainable models by design. © 2023 CEUR-WS. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Int-BEB: Enhanced Binary Exponential Backoff using Q-learning 5

Int-BEB: Enhanced Binary Exponential Backoff using Q-learnin...

引用

5th International Conference on Pattern Analysis and Intelligent Systems, PAIS 2023

作者： Zerguine, N. Ferhat Abbas Setif 1 University Networks and Distributed Systems Laboratory Department of Computer Science Setif Algeria

ISBN: (纸本)9798350381450

Because of their development and success, MANETs are now preferred alternatives in many fields of study and application. The IEEE 802.11 standard is the basis of most wireless technologies. To treat collisions in wireless networks, IEEE 802.11 Distributed Coordination Function (DCF) MAC layer employs Binary Exponential Backoff (BEB) algorithm, that is helpful in decreasing the potential of collision, but comes at the expense of several network performance metrics, such as medium access delay, bandwidth management, power use, and fairness. A Deep Learning technique called Deep Reinforcement Learning (DRL) allows an agent to communicate with the environment in order to accomplish a goal. In the present paper, we suggest Q-learning (QL), one of the DRL approaches to improve the Binary Exponential Backoff (BEB) in MANETs. The intelligently designed Int-BEB aims for better CW selection;this selection strikes to reduce collisions as much as possible and to give more chances to nodes that make collisions to access the channel by taking into consideration their residual energy. In-depth simulations are performed to evaluate the performance of the proposed mechanism. The performance of Int-BEB is evaluated in diverse networks with several criteria such as packet successful transmission, packet loss and energy. © 2023 IEEE.

关键词： Reinforcement learning

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：