检索结果-内蒙古大学图书馆

34th Annual International Conference on Collaborative Advances in Software and Computing, CASCON 2024

作者： Topal, Mustafa Burak Bozanta, Aysun Basar, Ayse Bogazici University Computer Engineering Istanbul Turkey Bogazici University Management Information Systems Istanbul Turkey Toronto Metropolitan University Data Science Laboratory TorontoON Canada

ISBN: (纸本)9798331504830

In this study, we explore the performance of large language models (LLMs) and provide insights into the strengths and weaknesses of these models in sentiment analysis. In addition, we explore the impact of various instruction methods and fine-tuning techniques on the models' performance and analyze how sensitive they are to different prompts. Although there are studies comparing LLMs on sentiment analysis tasks, there is a limited number of studies on fine-tuning strategies, instruction variety, and prompt sensitivity of LLMs for sentiment analysis. For this purpose, we used Llama2-7B, Lama3-8B, Mistral-7B, Gemma-7B, and Bloom-7B and compared them with BERT and Roberta. We evaluated fine-tuned and original chat versions with zero and few-shot experiments. We generated various instruction strategies and observed their effects on the performance of the models. We also compared Quantized Low-Rank Adapters (QLoRA) fine-tuning and full fine-tuning with all parameters. The fine-tuned versions performed better compared to the original chat versions on almost all tasks. The fine-tuned and chat versions of Llama3-8B and Mistral-7B outperformed others on these tasks, while the Llama2-7B-chat model often produced invalid responses. Our research indicates that QLoRA is a practical substitute for full fine-tuning, as it lessens computational demands without sacrificing performance. Fine-tuned models were less affected by variations in test prompts compared to chat models. This is likely because their specialized training allows them to better handle queries within their domain. In this exploratory study, we provide insights into the potential of LLMs in sentiment analysis tasks. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Photonic Topological Spin Pump in Synthetic Frequency Dimensions

引用

Physical Review Letters 2024年第3期132卷 033803-033803页

作者： Joseph Suh Gyunghun Kim Hyungchul Park Shanhui Fan Namkyoo Park Sunkyu Yu Intelligent Wave Systems Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul 08826 Korea Department of Electrical Engineering Ginzton Laboratory Stanford University Stanford California 94305 USA Photonic Systems Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul 08826 Korea

Reducing geometrical complexity while preserving desired wave properties is critical for proof-of-concept studies in wave physics, as evidenced by recent efforts to realize photonic synthetic dimensions, isospectrality, and hyperbolic lattices. Laughlin’s topological pump, which elucidates quantum Hall states in cylindrical geometry with a radial magnetic field and a time-varying axial magnetic flux, is a prime example of these efforts. Here we propose a two-dimensional dynamical photonic system for the topological pumping of pseudospin modes by exploiting synthetic frequency dimensions. The system provides the independent control of pseudomagnetic fields and electromotive forces achieved by the interplay between mode-dependent and mode-independent gauge fields. To address the axial open boundaries and azimuthal periodicity of the system, we define the adjusted local Chern marker with rotating azimuthal coordinates, proving the nontrivial topology of the system. We demonstrate the adiabatic pumping for crosstalk-free frequency conversion with wave front molding. Our approach allows for reproducing Laughlin’s thought experiment at room temperature with a scalable setup.

关键词： Photonics Synthetic gauge fields Topological effects in photonic systems Coupled mode theory

来源：评论

学校读者我要写书评

暂无评论

ZKP Protocols for Usowan,Herugolf,and Five Cells

引用

Tsinghua Science and Technology 2024年第6期29卷 1651-1666页

作者： Daiki Miyahara Léo Robert Pascal Lafourcade Takaaki Mizuki Graduate School of Informatics and Engineering The University of Electro-CommunicationsTokyo 1828585Japan MIS Lab University of Picardy Jules VerneAmiens 80000France Laboratory of Computer Science Modelling and Systems OptimisationUniversity of Clermont AuvergneClermont-Ferrand 63178France Cyberscience Center Tohoku UniversitySendai 9808578Japan

A Zero-Knowledge Proof (ZKP) protocol allows a participant to prove the knowledge of some secret without revealing any information about it. While such protocols are typically executed by computers, there exists a line of research proposing physical instances of ZKP protocols. Up to now, many card-based ZKP protocols for pen-and-pencil puzzles, like Sudoku, have been designed. Those games, mostly edited by Nikoli, have simple rules, yet designing them in card-based ZKP protocols is non-trivial. In this work, we propose a card-based ZKP protocol for Usowan, a Nikoli game. In Usowan, for each room of a puzzle instance, there is exactly one piece of false information. The goal of the game is to detect this wrong data amongst the correct data and also to satisfy the other rules. Designing a card-based ZKP protocol to deal with the property of detecting a liar has never been done. In some sense, we propose a physical ZKP for hiding of a liar. This work extends a previous paper appearing in Ref. [1]. In this extension, we propose two other protocols, for Herugolf and Five Cells. The puzzles are specifically chosen because each of those three puzzles shares a common constraint, connectivity. However, showing the connected configuration cannot be done with generic approach and brings new construction to the existing connectivity ZKP protocol. Indeed, in Herugolf, the connectivity is handled with a given length of cell which is decremental (i.e., the length of each connected cell decreases by one at each step). For Five Cells, there is an additional step in the setup allowing to encode all the information needed to ensure a valid ZKP protocol.

关键词： Zero-Knowledge Proof(ZKP)protocol playing cards card-based cryptography physical assumptions Usowan Herugolf FiveCells

来源：评论

学校读者我要写书评

暂无评论

Adaptive Methods for Kernel Initialization of Convolutional Neural Network Model Applied to Plant Disease Classification 11

Adaptive Methods for Kernel Initialization of Convolutional ...

引用

11th IEEE Open Conference of Electrical, Electronic and Information Sciences, eStream 2024

作者： Lagnaoui, Saloua Boumais, Khaoula Fallah, Saad El En-Naimani, Zakariae Haddouch, Khalid Matuzevicius, Dalius ENSA Sidi Mohamed Ben Abdellah University Laboratory Engineering Systems and Applications Fez Morocco Sidi Mohammed Ben Abdallah University ENSA Laboratory AI Data Science and Emerging Systems Fez Morocco Private University of Fez Systems and Sustainable Environment Laboratory Faculty of Engineering Sciences Fez Morocco ENSET Laboratory Computer Science AI and Cyber Security University of Hassan II Casablanca Mohammedia Morocco Vilnius Gediminas Technical University Faculty of Electronics Department of Electronic Systems Vilnius Lithuania

ISBN: (纸本)9798350352412

Convolutional Neural Networks are instrumental in artificial intelligence, especially in image processing, where their ability to autonomously learn hierarchical features has led to significant breakthroughs. However, the success of these models is intricately tied to the judicious choice of hyperparameters, which include the configuration of convolutional layers, activation functions, and kernel initialization methods. This research explores kernel initialization methods in Convolutional Neural Network models, seven diverse initialization methods (Glorot Uniform, Ones initialization, Zero initialization, Constant initialization, Random initialization, HeNormal initialization, and Orthogonal initialization) are comprehensively compared. The primary objective is to showcase the sensitivity of Convolutional Neural Networks to these various initialization techniques. The study not only aims to reveal the nuanced impact of kernel initialization but also introduces an adaptive method to enhance model performance. By delving into the intricacies of initialization methods, this research contributes to the improvement of Convolutional Neural Networks effectiveness, especially in critical applications like Plant Disease classification. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Counterfactual discriminative micro-expression recognition

引用

Visual Intelligence 2024年第1期2卷 1-10页

作者： Li, Yong Liu, Menglin Lao, Lingjie Wang, Yuanzhi Cui, Zhen Department of Computer Science City University of Hong Kong 999077 Hong Kong School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China

Micro-expressions are spontaneous, rapid and subtle facial movements that can hardly be suppressed or fabricated. Micro-expression recognition (MER) is one of the most challenging topics in affective computing. It aims to recognize subtle facial movements which are quite difficult for humans to perceive in a fleeting period. Recently, many deep learning-based MER methods have been developed. However, how to effectively capture subtle temporal variations for robust MER still perplexes us. We propose a counterfactual discriminative micro-expression recognition (CoDER) method to effectively learn the slight temporal variations for video-based MER. To explicitly capture the causality from temporal dynamics hidden in the micro-expression (ME) sequence, we propose ME counterfactual reasoning by comparing the effects of the facts w.r.t. original ME sequences and the counterfactuals w.r.t. counterfactually-revised ME sequences, and then perform causality-aware prediction to encourage the model to learn those latent ME temporal cues. Extensive experiments on four widely-used ME databases demonstrate the effectiveness of CoDER, which results in comparable and superior MER performance compared with that of the state-of-the-art methods. The visualization results show that CoDER successfully perceives the meaningful temporal variations in sequential faces. © The Author(s) 2024.

关键词： Affective computing Causal graph Counterfactual reasoning Micro-expression recognition Temporal variation

来源：评论

学校读者我要写书评

暂无评论

Why Go Full? Elevating Federated Learning Through Partial Network Updates 38

Why Go Full? Elevating Federated Learning Through Partial Ne...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Guo, Wenkai Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo BuffaloNY United States Zhongguancun Laboratory Beijing China

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neuro-symbolic artificial intelligence: a survey

引用

Neural Computing and Applications 2024年第21期36卷 12809-12844页

作者： Bhuyan, Bikram Pratim Ramdane-Cherif, Amar Tomar, Ravi Singh, T.P. LISV Laboratory University of Paris Saclay 10-12 Avenue of Europe Velizy78140 France School of Computer Science University of Petroleum and Energy Studies Uttarakhand Bidholi Dehradun248006 India Persistent Systems Pune Mumbai411016 India School of Computer Science Engineering and Technology Bennett University Greater Noida201306 India

The goal of the growing discipline of neuro-symbolic artificial intelligence (AI) is to develop AI systems with more human-like reasoning capabilities by combining symbolic reasoning with connectionist learning. We survey the literature on neuro-symbolic AI during the last two decades, including books, monographs, review papers, contribution pieces, opinion articles, foundational workshops/talks, and related PhD theses. Four main features of neuro-symbolic AI are discussed, including representation, learning, reasoning, and decision-making. Finally, we discuss the many applications of neuro-symbolic AI, including question answering, robotics, computer vision, healthcare, and more. Scalability, explainability, and ethical considerations are also covered, as well as other difficulties and limits of neuro-symbolic AI. This study summarizes the current state of the art in neuro-symbolic artificial intelligence. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Digital Twins for Creating Virtual Models of Solar Photovoltaic Plants

Digital Twins for Creating Virtual Models of Solar Photovolt...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： George, Deborah Venayagamoorthy, Ganesh K. Clemson University Real-Time Power and Intelligent Systems Laboratory Department of Electrical and Computer Engineering ClemsonSC29634 United States

ISBN: (纸本)9781665430654

Amidst the challenges posed by the high penetration of distributed energy resources (DERs), particularly a number of distributed photovoltaic plants (DPVs), in modern electric power distribution systems (MEPDS), the integration of new technologies and frameworks become crucial for addressing operation, management, and planning challenges. Situational awareness (SA) and situational intelligence (SI) over multi-time scales is essential for enhanced and reliable PV power generation in MEPDS. In this paper, data-driven digital twins (DTs) are developed using AI paradigms to develop actual and/or virtual models of DPV s, These DTs are then applied for estimating and forecasting the power outputs of physical and virtual PV plants. Virtual weather stations are used to estimate solar irradiance and temperature at user-selected locations in a localized region, using inferences from physical weather stations. Three case studies are examined based on data availability: physical PV plant, hybrid PV plants, and virtual PV plants, generating real-time estimations and short-term forecasts of PV power production that can support distribution system studies and decision-making. © 2023 IEEE.

关键词： - AI digital twin distributed energy resources power distribution systems virtual systems weather stations

来源：评论

学校读者我要写书评

暂无评论

Handwriting Recognition in Historical Manuscripts Using a Deep Learning Approach

Handwriting Recognition in Historical Manuscripts Using a De...

引用

International Conference on Advanced Intelligent systems for Sustainable Development, AI2SD 2022

作者： El Bahi, Hassan Laboratory of Computer and Systems Engineering L2IS Cadi Ayyad University B.P. 511 Marrakech40000 Morocco

ISBN: (纸本)9783031263835

The ancient manuscripts are considered one of the most important and valuable treasures of the cultural heritage of nations. A great effort has been made in recent decades to digitize and make the contents of these manuscripts available to everyone, but only a very small percentage of these manuscripts are accessible to the public. In this context, we propose in this paper a system for the recognition of handwritten text in ancient manuscripts. The system begins with a pre-processing step which aims to improve the quality and eliminate degradations in the input images. Next, a convolutional neural network (CNN) model is adapted to perform the step of extracting the most relevant features from each text word image. Next, the classification phase is carried out using the recurrent neuron network RNN with long short-term memory (LSTM) block and connectionist temporal classification (CTC) layer, which predicts the sequence of characters that represents the text included in each input word image. The experimentation of the proposed system is performed on the ESPOSALLES dataset, and the performance results show promising recognition rates. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Redirected Walking Techniques:Taxonomy,Methods,and Future Directions

引用

Journal of computer Science & Technology 2022年第3期37卷 561-583页

作者： Yi-Jun Li Frank Steinicke Miao Wang State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Department of Informatics Universität HamburgHamburg 20146Germany Peng Cheng Laboratory Shenzhen 518055China

Virtual reality(VR)allows users to explore and experience a computer-simulated virtual environment so that VR users can be immersed in a totally artificial virtual world and interact with arbitrary virtual ***,the limited physical tracking space usually restricts the exploration of large virtual spaces,and VR users have to use special locomotion techniques to move from one location to *** these techniques,redirected walking(RDW)is one of the most natural locomotion techniques to solve the problem based on near-natural walking *** core idea of the RDW technique is to imperceptibly guide users on virtual paths,which might vary from the paths they physically walk in the real *** a similar way,some RDW algorithms imperceptibly change the structure and layout of the virtual environment such that the virtual environment fits into the tracking *** this survey,we first present a taxonomy of existing RDW *** on this taxonomy,we compare and analyze both contributions and shortcomings of the existing methods in detail,and find view manipulation methods offer satisfactory visual effect but the experience can be interrupted when users reach the physical boundaries,while virtual environment manipulation methods can provide users with consistent movement but have limited application ***,we discuss possible future research directions,indicating combining artificial intelligence with this area will be effective and intriguing.

关键词： virtual reality locomotion redirected walking

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：