检索结果-内蒙古大学图书馆

41st International Conference on machine learning, ICML 2024

作者： Munteanu, Alexander Omlor, Simon Dortmund Data Science Center Faculties of Statistics and Computer Science TU Dortmund University Dortmund Germany Faculty of Statistics TU Dortmund University Dortmund Germany Lamarr-Institute for Machine Learning and Artificial Intelligence Dortmund Germany

The turnstile data stream model offers the most flexible framework where data can be manipulated dynamically, i.e., rows, columns, and even single entries of an input matrix can be added, deleted, or updated multiple times in a data stream. We develop a novel algorithm for sampling rows ai of a matrix A ∈ Rn×d, proportional to their p norm, when A is presented in a turnstile data stream. Our algorithm not only returns the set of sampled row indexes, it also returns slightly perturbed rows ãi ≈ ai, and approximates their sampling probabilities up to Ε relative error. When combined with preconditioning techniques, our algorithm extends to p leverage score sampling over turnstile data streams. With these properties in place, it allows us to simulate subsampling constructions of coresets for important regression problems to operate over turnstile data streams with very little overhead compared to their respective off-line subsampling algorithms. For logistic regression, our framework yields the first algorithm that achieves a (1 + Ε) approximation and works in a turnstile data stream using polynomial sketch/subsample size, improving over O(1) approximations, or exp(1/Ε) sketch size of previous work. We compare experimentally to plain oblivious sketching and plain leverage score sampling algorithms for p and logistic regression. Copyright 2024 by the author(s)

关键词： data streams

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Heterogeneous Ensemble Methods for Re-Identification 23

On the Effectiveness of Heterogeneous Ensemble Methods for R...

引用

23rd IEEE International Conference on machine learning and Applications, ICMLA 2024

作者： Klüttermann, Simon Rutinowski, Jérôme Polachowski, Frederik Nguyen, Anh Grimme, Britta Roidl, Moritz Müller, Emmanuel Paderborn University Paderborn Germany Tu Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany Research Center Trustworthy Data Science and Security Dortmund Germany

ISBN: (纸本)9798350374889

In this contribution, we introduce a novel ensemble method for the re-identification of industrial entities, using images of chipwood pallets and galvanized metal plates as dataset examples. Our algorithms replace commonly used, complex siamese neural networks with an ensemble of simplified, rudimentary models, providing wider applicability, especially in hardware-restricted scenarios. Each ensemble sub-model uses different types of extracted features of the given data as its input, allowing for the creation of effective ensembles in a fraction of the training duration needed for more complex state-of-the-art models. We reach state-of-the-art performance at our task, with a Rank-1 accuracy of over 77% and a Rank-10 accuracy of over 99%, and introduce five distinct feature extraction approaches, and study their combination using different ensemble methods. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

machine learning and Deep learning Approaches for Automated Diabetic Retinopathy Diagnosis

Machine Learning and Deep Learning Approaches for Automated ...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Fulkar, Bhushan Burle, Rushikesh Patil, Pawan Gaurkhade, Sanskruti Gundewar, Swapnil Pacharaney, Utkarsha Datta Meghe Institute of Higher Education and Research Department of Artificial Intelligence and Data Science Wardha India Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Department of Computer Science and Design Wardha India Datta Meghe Institute of Higher Education and Research Department of Artificial Intelligence and Machine Learning Wardha India

ISBN: (纸本)9798350375237

Since diabetic retinopathy (DR) is the primary cause of blindness in working-age adults worldwide, vision loss must be avoided by receiving early detection and treatment. In recent years, deep learning techniques have become more and more useful tools for automated drug discovery, possibly offering solutions to overcome the limitations of traditional screening methods. In-depth descriptions of the most recent deep learning methods for DR detection are provided in this review article. We begin by discussing the importance of DR screening, its prevalence, and the challenges faced by healthcare systems in managing this condition. Next, we discuss different deep learning architectures used for DR detection, such as CNNs and RNNs, and their combinations. We investigate how to improve the precision, resilience, and interpretability of DR detection models through the use of explainable AI, ensemble methods, transfer learning, and attention mechanisms. We also examine publicly available datasets, evaluation metrics, and preprocessing techniques that are commonly used to benchmark DR detection algorithms. We discuss the limitations and possible uses of deep learning-based deep readout detection, emphasizing the significance of large-scale, diverse datasets, the interpretability of the model, and real-world deployment concerns. The overall objectives of this review are to advance the field of automated DR detection by highlighting recent developments, compiling existing knowledge, and identifying areas that require further research. © 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

Optimized Automated Stock Trading using DQN and Double DQN

Optimized Automated Stock Trading using DQN and Double DQN

引用

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

作者： Gurudutt S Bharadwaj David Pratap Narayana Darapaneni Department of Computer Science PES University Bengaluru India Department of Data Science and Machine Learning Great Learning Bengaluru India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

Stock Portfolio management involves managing the buying, holding and selling decisions for the various stocks in the portfolio. There has been work where Reinforcement learning (RL) based actor-critic methods like Deep Direct Policy Gradient (DDPG) have been used for asset allocation problems. Here an attempt has been made to use solely critic-based value function methods like Deep Q-network (DQN) and Double DQN for estimating Q-values of market actions. Then, an optimized portfolio management algorithm designed to balance trades across a basket of stocks is designed. Five stocks are chosen of different price ranges from NYSE and NASDAQ stock exchanges. The average cumulative percentage returns provided by DQN was 55% on testing data with an average Maximum Drawdown (MDD) of 2.5%. The same with Double DQN was 71% on testing data with an average MDD of 2.83%. These results were significantly better than the case when a traditional Buy and Hold strategy was to be employed.

关键词： Reinforcement learning Resource management Stock markets Portfolios Computational intelligence Testing

来源：评论

学校读者我要写书评

暂无评论

Social Distancing Detection AI System using YOLO

Social Distancing Detection AI System using YOLO

引用

2023 International Conference on Computer, Electronics and Electrical Engineering and their Applications, IC2E3 2023

作者： Karthiga, M. Kavitha, D. Coimbatore Institute of Technology Dept of Artificial Intelligence and Data Science Coimbatore India Coimbatore Institute of Technology Dept. of Artificial Intelligence and Machine Learning Coimbatore India

ISBN: (纸本)9798350338003

The number of reported COVID-19 cases has once again increased due to the recent spread of the H3N2 virus. Even with vaccinations and medications, social distancing remains the most effective way to prevent the spread of these viruses. To address this issue, this paper proposes an automated system for monitoring social distancing in public places. The system utilizes a YOLOv3 object detection model to detect pedestrians in video frames captured by a camera. The frames are then converted to a top-down perspective to measure the distances between individuals in a 2D plane. If any individuals are too close to each other, the system displays a warning by highlighting them with a red frame and a red line. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

RainScaler: A Physics-Inspired Network for Precipitation Correction and Downscaling

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhao, Shan Xiong, Zhitong Zhu, Xiao Xiang Department of Data Science in Earth Observation Ottobrunn85521 Germany Munich Center for Machine Learning Munich80333 Germany

Spatial downscaling of precipitation, in which fine-grained regional precipitation patterns are recovered from coarse-resolution images, plays a crucial role in various weather and meteorological analyses. However, the intricate noise information presented in the observation data intertwines with the fine-scale characteristics, which poses challenges for subsequent feature extraction. Regional precipitation suffers from complex spatial patterns. Moreover, the real observatory data contains information inconsistent with the established physical principle, due either to inaccurate or incomplete physical models or limited data quality, thus making the implementation of physically informed deep learning (DL) more difficult. For example, strong physical constraints may lead to over-regularization, in which the model becomes too rigid and fails to capture certain complexities in the data. In this work, we propose RainScaler, a physics-inspired deep neural network, to tackle these issues. First, to remove the noise and preserve the vital precipitation patterns effectively, the proposed RainScaler exploits an inconsistency-aware (IA) Denoising Net to explicitly model the spatial variability of noise in the input. In addition, a graph module is designed to learn the geographical-dependent fine-grained patterns in high-dimensional feature space at a moderate computation cost. Finally, multiscale physical constraints are skillfully embedded to incorporate additional insights into the data-driven framework. We test our approach on a public dataset consisting of over 60000 real low-resolution (LR) and high-resolution (HR) precipitation map pairs collected by different sensors. Our method produces realistic-looking precipitation maps with better discernment capability and corrects the structural error of precipitation distribution, especially for extreme events. Moreover, we evaluate the potential risks of incorporating physical constraints in real-world data applications. Our me

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Spatial Resolution of Aerial Images using a Deep Generative Approach with Multi-Stage Residual Refinement

Enhancing the Spatial Resolution of Aerial Images using a De...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and Engineering science, AMATHE 2024

作者： Shree Hari, B. Joy, Emmanuel Aroma, Jenice Division Of Data Science And Cyber Security Karunya Institute Of Technology And Sciences Coimbatore India Division Of Artificial Intelligence And Machine Learning Karunya Institute Of Technology And Sciences Coimbatore India Mgk Logistics Madurai India

ISBN: (纸本)9798350371567

Aerial images are photos taken from above, usually from planes or drones, displaying a landscape as seen from above. High-quality aerial images are crucial in various tasks, like precision agriculture, post-disaster monitoring, and land use classification. However, acquiring these images can be challenging due to the constraints of underlying image sensors and several other factors. This paper introduces a deep generative approach to enhance the spatial resolution of aerial imagery. The proposed method uses an Enhanced Deep Super-Resolution (EDSR) model architecture with a multi-stage residual refinement strategy. This particular model is comprised of residual blocks with two convolutional layers and residual connections. Through a succession of these residual blocks, the model processes low-resolution, 3-channel aerial images and finally upscales the images with a convolutional layer and a depth-to-space transformation. By increasing the spatial resolution of aerial imagery, this deep generative method seeks to overcome the problems that low-quality images present in real-world applications. Findings from the experiment on the VEDAI dataset demonstrate the effectiveness of the proposed method in producing high-quality aerial images. The improvements of PSNR and SSIM metrics by 1.05% and 0.34% respectively and the reduction in MAE and NRMSE by 0.0045 and 1.23% highlight its potential impact on various fields that depend on accurate and comprehensive aerial information. The outcomes of this work will contribute to the future development of picture super-resolution techniques for use in remote sensing and geospatial analysis. © 2024 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

AgentFusion: A Multi-Agent Approach to Accurate Text Generation

AgentFusion: A Multi-Agent Approach to Accurate Text Generat...

引用

Electrical and Computer Engineering Researches (ICECER), International Conference on

作者： Yasser Saeid Thomas Kopinski Machine Learning - Data Science South Westphalia University of Applied Sciences Meschede Germany

ISBN: (数字)9798331539733

ISBN: (纸本)9798331539740

The rise of large language models (LLMs) like Chat-GPT has significantly transformed the field of natural language processing (NLP). These models are now central to many companies' operations due to their capabilities in generating human-like text, understanding context, and responding to queries with high fluency. However, LLMs are not without flaws. They sometimes generate inaccurate or even completely fabricated information-a phenomenon known as “hallucination.” This issue underscores the increasing importance of Retrieval-Augmented Generation (RAG) systems, which aim to enhance the accuracy of LLM outputs by incorporating data from external sources. RAG systems are especially valuable when dealing with non-English content, such as German-language tasks, where high-quality data retrieval is crucial for achieving accurate results. Developing an effective RAG system, however, is complex and requires careful consideration of several critical elements. In this paper, we present a new approach to RAG, which we refer to as an “agentic RAG” system. This system utilizes three distinct agents that collaborate to optimize the output. We rigorously tested this system across various types of embeddings and benchmarked its performance against GPT-4. Our results indicate that the agentic RAG system significantly improves accuracy, particularly for German-language content, achieving a 24/25 accuracy score in tasks related to reactor decommissioning, finance, and sports domains. These results demonstrate the broad applicability and performance gains of agentic RAG systems in multilingual NLP tasks.

关键词： Accuracy Large language models Computational modeling Retrieval augmented generation Finance Benchmark testing Natural language processing data models Inductors Optimization

来源：评论

学校读者我要写书评

暂无评论

Multilingual Facial Emotion Decoding and Posture Recognition using Random Forest Classifier

Multilingual Facial Emotion Decoding and Posture Recognition...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Sangeetha, K. Balaji, V.S. Manju, M. Renuka Devi, S. Velayutham, P. Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology Chennai India

ISBN: (纸本)9798350374933

Effective communication is crucial for success in various interactions, including personal and online interviews. The work proposed is to refine the communication effectiveness and extend the understanding of interactions by incorporating new system functions of real-time emotion and body language capture. Facial and body landmarks are analyzed using Google’s Mediapipe to ensure accurate identification of the frequently performed emotions and frequently posed postures. The proposed system uses three classifiers, namely Random Forest, Gradient Boosting, and Ridge Classifier, all integrated in one pipeline;this makes our work distinct. In the testing phase the classifiers are checked to avoid misidentification of emotions or incorrect posture in different situations. One of the major novelties of this work is its ability to address users of different languages, thus it is relevant anywhere in the world. This dynamic and robust system provides accurate emotion analysis achieving the accuracy of 92%, enhancing understanding in various communication contexts and setting a new standard for interview and interaction analysis. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling 38

Structured Multi-Track Accompaniment Arrangement via Style P...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Jingwei Xia, Gus Wang, Ziyu Wang, Ye Institute of Data Science NUS Singapore School of Computing NUS Singapore Integrative Sciences and Engineering Programme NUS Graduate School Singapore Machine Learning Department MBZUAI United Arab Emirates Computer Science Department NYU Shanghai China

In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing computational efficiency. In this paper, we introduce a novel system that leverages prior modelling over disentangled style factors to address these challenges. Our method presents a two-stage process: initially, a piano arrangement is derived from the lead sheet by retrieving piano texture styles;subsequently, a multi-track orchestration is generated by infusing orchestral function styles into the piano arrangement. Our key design is the use of vector quantization and a unique multi-stream Transformer to model the long-term flow of the orchestration style, which enables flexible, controllable, and structured music generation. Experiments show that by factorizing the arrangement task into interpretable sub-stages, our approach enhances generative capacity while improving efficiency. Additionally, our system supports a variety of music genres and provides style control at different composition hierarchies. We further show that our system achieves superior coherence, structure, and overall arrangement quality compared to existing baselines. © 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

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：