检索结果-内蒙古大学图书馆

20th International Conference on Autonomous Agents and Multiagent systems, AAMAS 2021

作者： Castellini, Jacopo Devlin, Sam Oliehoek, Frans A. Savani, Rahul Dept. of Computer Science University of Liverpool Liverpool United Kingdom Microsoft Research Cambridge Cambridge United Kingdom Dept. of Intelligent Systems Delft University of Technology Delft Netherlands

ISBN: (纸本)9781713832621

Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many of these methods is multi-agent credit assignment: assessing an agent's contribution to the overall performance, which is crucial for learning good policies. We propose a novel algorithm called *** that explicitly tackles this by combining difference rewards with policy gradients to allow for learning decentralized policies when the reward function is known. By differencing the reward function directly, *** avoids difficulties associated with learning the Q-function as done by Counterfactual Multiagent Policy Gradients (COMA), a state-of-the-art difference rewards method. For applications where the reward function is unknown, we show the effectiveness of a version of *** that learns a reward network that is used to estimate the difference rewards. © 2021 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

Enhancing Ship Detection on Satellite Images with Modified DeepLabV3+

Enhancing Ship Detection on Satellite Images with Modified D...

引用

Artificial Intelligence and Emerging Technology (Global AI Summit), International Conference on

作者： Rohit Sharma Shubham Dahatonde Srimanta Kumar Acharjya Sourabh Singh Verma Vijaypal Singh Dhaka Ramesh Singh Rawat School Of Computing & Intelligent Systems Manipal University Jaipur Jaipur India Department of Computer Science and engineering C. V Raman Global University Bhubaneswar India Dept. of computer Science and Engg Graphic Era deemed to be University Deharadun Uttrakhand India

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

This paper presents a advance approach for ship detection in satellite imagery utilizing a modified DeepLabV3+ architecture, specifically designed to overcome the challenges inherent in such data. The proposed model features an enhanced feature extraction process and a refined atrous spatial pyramid pooling (ASPP) module, which together improve the detection of ships across various sizes and shapes. Comprehensive experiments on publicly available satellite datasets reveal that the modified DeepLabV3+ significantly outperforms existing state-of-the-art methods, achieving an accuracy of 98%. These findings demonstrate the model's robust ability to identify and localize ships in complex maritime settings, offering promising potential for improved maritime situational awareness and operational efficiency.

关键词： Training Image segmentation Accuracy Land surface Feature extraction Data models Robustness Satellite images Marine vehicles Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Just the Right Amount of Exercise: Aerobic Exercise and Memory

Just the Right Amount of Exercise: Aerobic Exercise and Memo...

引用

Adjunct Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable computers

作者： Andrew Vargo Kentaro Ohara Takumi Nakai Koichi Kise Graduate School of Informatics Osaka Metropolitan University Japan Osaka Prefecture University Japan Dept. of Computer Science and Intelligent Systems Osaka Prefecture University Japan

ISBN: (纸本)9781450394239

A popular perception is that aerobic exercises are effective for improving performance on memory tasks. However, previous studies have not yet explored the effectiveness of aerobic exercise for individuals. We investigate the effects of aerobic exercise on English vocabulary learning by managing the conditions under which aerobic exercise is effective for individuals. We use a heart-rate sensor to control the amount of exertion a participant made on a treadmill while learning the vocabulary words. The results show this method can improve memory retention. This indicates that close monitoring of individual aerobic exertion through physiological sensing can make improved learning with exercise a reality.

关键词： physiological sensing ubiquitous sensing augmented learning

来源：评论

学校读者我要写书评

暂无评论

Controlled Dropout for Uncertainty Estimation

Controlled Dropout for Uncertainty Estimation

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Mehedi Hasan Ibrahim Hossain Ashikur Rahman Saeid Nahavandi Institute for Intelligent Systems Research and Innovation Deakin University Geelong VIC Australia Dept. of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh

Uncertainty quantification in a neural network is one of the most discussed topics for safety-critical applications. Though Neural Networks (NNs) have achieved state-of-the-art performance for many applications, they still provide unreliable point predictions, which lack information about uncertainty estimates. Among various methods to enable neural networks to estimate uncertainty, Monte Carlo (MC) dropout has gained much popularity in a short period due to its simplicity. In this study, we present a new version of the traditional dropout layer where we are able to fix the number of dropout configurations. As such, each layer can take and apply the new dropout layer in the MC method to quantify the uncertainty associated with NN predictions. We conduct experiments on both toy and realistic datasets and compare the results with the MC method using the traditional dropout layer. Performance analysis utilizing uncertainty evaluation metrics corroborates that our dropout layer offers better performance in most cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-tuned Large Language Models (LLMs): Improved Prompt Injection Attacks Detection

arXiv

引用

arXiv 2024年

作者： Rahman, Md Abdur Wu, Fan Cuzzocrea, Alfredo Ahamed, Sheikh Iqbal Dept. of Intelligent Systems and Robotics University of West Florida FL United States Department of Computer Science Tuskegee University TuskegeeAL United States iDEA Lab University of Calabria Rende Italy Department of Computer Science Marquette University WI United States

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks, which poses a critical problem. These attacks target LLMs applications through using carefully designed input prompts to divert the model from adhering to original instruction, thereby it could execute unintended actions. These manipulations pose serious security threats which potentially results in data leaks, biased outputs, or harmful responses. This project explores the security vulnerabilities in relation to prompt injection attacks. To detect whether a prompt is vulnerable or not, we follows two approaches: 1) a pre-trained LLM, and 2) a fine-tuned LLM. Then, we conduct a thorough analysis and comparison of the classification performance. Firstly, we use pre-trained XLM-RoBERTa model to detect prompt injections using test dataset without any fine-tuning and evaluate it by zero-shot classification. Then, this proposed work will apply supervised fine-tuning to this pre-trained LLM using a task-specific labeled dataset from deepset in huggingface, and this fine-tuned model achieves impressive results with 99.13% accuracy, 100% precision, 98.33% recall and 99.15% F1-score thorough rigorous experimentation and evaluation. We observe that our approach is highly efficient in detecting prompt injection attacks. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RTBERT: A Transformer Based Approach for Improved Rumor Classification from Tweet

RTBERT: A Transformer Based Approach for Improved Rumor Clas...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Shakib Mahmud Dipto Mostofa Kamal Sagor Anatte Rozario Sahal Bin Saad Department of Computer Science and Engineering University of Liberal Arts Bangladesh (ULAB) Dhaka Bangladesh Dept. of CSE Computer Vision and Intelligent Systems (CVIS) Brac University Dhaka Bangladesh Department of Computer Science and Engineering Primeasia University Dhaka Bangladesh

In an era where both the general public and established news outlets increasingly rely on social media for real-time information, the abundance of rumors offers a huge difficulty. False information can have far-reaching implications, affecting individuals, communities, and even entire countries. To address this issue, a low-cost, self-regulating, and forward-thinking rumor detection technique is required. This research performs an intensive analysis of the performance of three robust machine learning algorithms, including XGBoost, SVM, and Random Forest, as well as two deep learning-based transformers, namely BERT and DistilBert. In this research, the models are trained and evaluated on a combined dataset comprising data from Twitter15 and Twitter16 datasets. Support Vector Machine (SVM) and Random Forest exhibit the best accuracy among classical machine learning models, reaching 89.05%. In comparison, among the transformer-based deep learning models, BERT achieves the best accuracy of 90.20%. In conclusion, the learning-based transformers beat its competitors in terms of accuracy, recall, precision, and F-measure, proving its efficacy in minimizing the detrimental impact of rumors on people, communities, and society as a whole.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical Evanescent Field for Direct Observation of Sub-100nm Particle Motion on Glass Surface

Optical Evanescent Field for Direct Observation of Sub-100nm...

引用

Robotics, Engineering, science, and Technology (RESTCON), International Conference on

作者： Panart Khajornrungruang Thitipat Permpatdechakul Keisuke Suzuki Aran Blattler Yutaka Terayama Daiki Goto Pipat Phaisalpanumas Natthaphon Bun-Athuek Amornphun Phunopas Dept. of Intelligent and Control System Faculty of Computer Science and Systems Engineering Mechanical Science and Technology Division Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Interdisciplinary Informatics Graduate School of Computer Science and Systems Engineering Mechanical Information Science and Technology Division Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Production and Robotics Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand Dept. of Intelligent and Control System Graduate School of Computer Science and Systems Engineering Mechanical Science and Technology Course Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Industiral Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand Dept. of Mechanical Engineering Technology College of Industrial Technology King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand

To directly investigate the dynamic nanoscale phenomenon on the surface being processed in wet conditions such as precision polishing, and cleaning in semiconductor industrial, an optical method for visualization and observation of each sub-100 nm sized particle that is moving on an interface such as a silica glass surface by applying an evanescent field have been proposing. Subsequently, we developed an experimental apparatus equipped with an optical microscopy system for verifying the moving particle observation method in a laboratory scale. This article introduces some experimentally direct observation results of duplicated wet processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simplicial Convolutional Filters

arXiv

引用

arXiv 2022年

作者： Yang, Maosheng Isufi, Elvin Schaub, Michael T. Leus, Geert Dept. of Intelligent Systems Delft University of Technology Netherlands Dept. of Computer Science RWTH Aachen University Germany Dept. of Microelectronics Delft University of Technology Netherlands

We study linear filters for processing signals supported on abstract topological spaces modeled as simplicial complexes, which may be interpreted as generalizations of graphs that account for nodes, edges, triangular faces, etc. To process such signals, we develop simplicial convolutional filters defined as matrix polynomials of the lower and upper Hodge Laplacians. First, we study the properties of these filters and show that they are linear and shift-invariant, as well as permutation and orientation equivariant. These filters can also be implemented in a distributed fashion with a low computational complexity, as they involve only (multiple rounds of) simplicial shifting between upper and lower adjacent simplices. Second, focusing on edge-flows, we study the frequency responses of these filters and examine how we can use the Hodge-decomposition to delineate gradient, curl and harmonic frequencies. We discuss how these frequencies correspond to the lower- and the upper-adjacent couplings and the kernel of the Hodge Laplacian, respectively, and can be tuned independently by our filter designs. Third, we study different procedures for designing simplicial convolutional filters and discuss their relative advantages. Finally, we corroborate our simplicial filters in several applications: to extract different frequency components of a simplicial signal, to denoise edge flows, and to analyze financial markets and traffic networks. © 2022, CC BY-SA.

关键词： Chebyshev polynomials

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Learning Approach to Detect Neurodegenerative Diseases Using Retinal Images

An Efficient Deep Learning Approach to Detect Neurodegenerat...

引用

computer science and Data Engineering (CSDE), IEEE Asia-Pacific Conference on

作者： Chowdhury Mohammad Irfanuddin Wasique Islam Shafin Koushik Ahmed Md. Hasib Khan Md. Ashraful Alam Rafeed Rahman Shakib Mahmud Dipto Department of Computer Science and Engineering Brac University Dhaka Bangladesh Dept. of CSE Computer Vision and Intelligent Systems (CVIS) Research Lab Brac University Dhaka Bangladesh Department of Computer Science and Engineering University of Liberal Arts Bangladesh (ULAB) Dhaka Bangladesh

Neurodegenerative disorders like Multiple Sclerosis, Parkinson's disease, and Alzheimer's disease typically get diagnosed through brain MRI, CT scans, genetic testing, and various laboratory screening tests that are often tedious, time-consuming, and beyond the reach of the financial capability of many people especially, those living in the developing world. Moreover, they often pose potential hazards for patients with certain pre-existing conditions. To remedy this, we propose an efficient deep-learning approach that enables the detection of such neurodegenerative diseases through retinal images rather than brain images. Our proposed system can proactively detect such disorders simply through retinal scans, which are fast and cost-effective compared to traditional diagnostic approaches, which require expensive and sophisticated equipment. We used a dataset containing retinal cross-sectional images of 21 Multiple Sclerosis patients and 14 healthy individuals for our research, and our model achieved 98.85% accuracy while classifying healthy and diseased individuals from retinal scans.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ontology-Based Method for Semantic Association Rules

Ontology-Based Method for Semantic Association Rules

引用

IEEE India Conference (INDICON)

作者： Abhilash C B Kavi Mahesh Dept. of Computer Science and Engineering Indian Institute of Information Technology Dharwad Dharwad India Dept. of Data Science and Intelligent Systems Indian Institute of Information Technology Dharwad Dharwad India

ISBN: (纸本)9781665452724

Finding interesting association rules is a popular and current topic in data mining. The Apriori family of algorithms is built around two rule extraction measures: support and confidence. Even though these two measures are easy to compute, they yield many rules, the majority of which are redundant and may not be of interest to the user. Also, by themselves, support and confidence do not generate strong rules. Additional measures are required to mine interesting facts from data. Ontologies have become the fundamental building blocks for structuring and formalizing data. With the semantic structuring of information, the implicit relationship between data elements makes the analyst get important facts from the data. Our study proposes a novel framework for interestingness in data by combining domain ontology with semantic interestingness measures. The ontology-based method infers rules that are semantically enriched and strong. We analyze the quality of the rule considering the factors defined by the domain experts. It is observed that our methodology generates semantically enriched rules that are more acceptable to domain experts.

关键词： COVID-19 Current measurement Semantics Knowledge based systems Influenza Ontologies Resource description framework

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：