检索结果-内蒙古大学图书馆

32nd Annual European Symposium on Algorithms, ESA 2024

作者： Arora, Vipul Bhattacharyya, Arnab Boban, Mathews Guruswami, Venkatesan Kelman, Esty School of Computing National University of Singapore Singapore Department of EECS Department of Mathematics University of California BerkeleyCA United States CSAIL Massachusetts Institute of Technology CambridgeMA United States Department of Computer Science Faculty of Computing & Data Sciences Boston University MA United States

ISBN: (纸本)9783959773386

We study the problem of robust multivariate polynomial regression: let p: Rn → R be an unknown n-variate polynomial of degree at most d in each variable. We are given as input a set of random samples (xi, yi) ∈ [−1, 1]n × R that are noisy versions of (xi, p(xi)). More precisely, each xi is sampled independently from some distribution χ on [−1, 1]n, and for each i independently, yi is arbitrary (i.e., an outlier) with probability at most ρ n log d), where the hidden constant depends on n, if χ is the n-dimensional Chebyshev distribution. The sample complexity is On(d2n log d), if the samples are drawn from the uniform distribution instead. The approximation error is guaranteed to be at most O(σ), and the run-time depends on log(1/σ). In the setting where each xi and yi are known up to N bits of precision, the run-time's dependence on N is linear. We also show that our sample complexities are optimal in terms of dn. Furthermore, we show that it is possible to have the run-time be independent of 1/σ, at the cost of a higher sample complexity. © Vipul Arora, Arnab Bhattacharyya, Mathews Boban, Venkatesan Guruswami, and Esty Kelman;licensed under Creative Commons License CC-BY 4.0.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

引用

Foundation and Large Language Models (FLLM), International Conference on

作者： Rajesh Pasupuleti Ravi Vadapalli Christopher Mader Norris Timothy Frost Institute for Data Science and Computing (IDSC) University of Miami Coral Gables FL USA

ISBN: (数字)9798350354799

ISBN: (纸本)9798350354805

For the public, understanding Large Language Models (LLMs) can be likened to recognizing how a well-trained assistant works—one that has read an extensive library of information on virtually every topic imaginable. Imagine an assistant that not only reads and remembers all this information but also learns the nuances of how words and ideas are connected across different contexts. This assistant can then use this knowledge to write articles, answer questions, compose emails, or even generate creative stories, all in a manner that feels surprisingly human. This capability comes from what's known as "transformer architecture," a type of design that helps the model pay attention to different parts of the text as it reads, making it adept at understanding and generating language. LLMs are a breakthrough in technology because they can understand and produce language with a level of subtlety and complexity that was previously unachievable, making them valuable tools across various industries. The paper aims to provide a comprehensive analysis of the transformative impact of LLMs across various enterprise sectors. It intends to contribute to the understanding of how LLMs can enhance efficiency, innovation, and decision-making processes in industries such as healthcare, finance, education, and in the software engineering sector. It also provides a comprehensive overview of current popular LLMs in Enterprise applications, in various domains, and discusses the Ethical, Technical, and Regulatory challenges, future trends, and developments in this dynamic field.

关键词： Industries Technological innovation Image recognition Large language models Finance Medical services Transformers Market research Libraries Software engineering

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Pose-Transformation and Radial Distance Clustering for Unsupervised Person Re-identification ov

arXiv

引用

arXiv 2024年

作者： Seth, Siddharth Sonth, Akash Chakraborty, Anirban Visual Computing Lab Department of Computational and Data Sciences Indian Institute of Science Bangalore India

Person re-identification (re-ID) aims to tackle the problem of matching identities across non-overlapping cameras. Supervised approaches require identity information that may be difficult to obtain and are inherently biased towards the dataset they are trained on, making them unscalable across domains. To overcome these challenges, we propose an unsupervised approach to the person re-ID setup. Having zero knowledge of true labels, our proposed method enhances the discriminating ability of the learned features via a novel two-stage training strategy. The first stage involves training a deep network on an expertly designed pose-transformed dataset obtained by generating multiple perturbations for each original image in the pose space. Next, the network learns to map similar features closer in the feature space using the proposed discriminative clustering algorithm. We introduce a novel radial distance loss, that attends to the fundamental aspects of feature learning - compact clusters with low intra-cluster and high inter-cluster variation. Extensive experiments on several large-scale re-ID datasets demonstrate the superiority of our method compared to state-of-the-art approaches. © 2024, CC BY.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

ASCM: Analysis of a Sequential and Collaborative Model for Recommendations

引用

SN Computer science 2024年第6期5卷 788页

作者： Tandon, Righa Verma, Ajay Gupta, P.K. Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Department of Computer Science and Engineering Jaypee University of Information Technology HP Solan 173 234 India Department of Data Science and Engineering School of Computing Mohan Babu University AP Tirupati 517 102 India

The recommender system can predict future lists of items based on the user’s sentiments and interactions. As the data is ubiquitous, we have a number of options available to make a selection. This is the scenario where the recommender system plays its role by narrowing the available options and making the selection process easy and effective. In this paper, we have proposed a sequential recommender system that considers the user interactions along with the items in sequential order and maps the sequences dynamically, in which the weight-age is given to current preferences and recent choices as explored by the user of the system. We have provided a detailed comparison of the proposed sequential recommender system with the commonly used matrix factorization model. The proposed recommender system is based on sequential dependencies and responds equally well to the cold start problem. We have obtained results using Movielens dataset, which reveal that the proposed recommender system is much faster with higher mean reciprocal rank (MRR) value. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Collaborative filtering Machine learning Matrix factorization Recommender systems Sequential model Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

A Mathematical Model to Minimize the Total Cultivation Cost of Sugarcane 11th

A Mathematical Model to Minimize the Total Cultivation Cost ...

引用

11th International Conference on Soft computing for Problem Solving, SocProS 2022

作者： Kumar, Sumit Pant, Millie Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Roorkee Uttarakhand Roorkee India Mehta Family School for Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Uttarakhand Roorkee India

ISBN: (纸本)9789811965241

In the present study, a non-linear mathematical model is proposed to minimize the total expenditure made on sugarcane cultivation. The objective here is to optimize the costs involved in transportation, cultivation, and management of the deterioration of sugarcane. The optimization tools used are Differential Evolution (DE) and Particle Swarm Optimization (PSO). Further, the model is validated by comparing the actual expenditure of sugarcane cultivation with results obtained by PSO and DE, which indicates that the application of optimization methods may help in reducing the expenditure made on sugarcane cultivation. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Efficiency Assessment of an institute Through Parallel Network data Envelopment Analysis 11th

Efficiency Assessment of an Institute Through Parallel Netwo...

引用

11th International Conference on Soft computing for Problem Solving, SocProS 2022

作者： Kumar, Atul Panwar, Ankita Pant, Millie Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Roorkee Roorkee247667 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Roorkee247667 India

ISBN: (纸本)9789811965241

Conventional data envelopment analysis (DEA) is a non-parametric approach to examine the efficiency of similar decision-making units (DMUs) as a whole system without considering its internal structure, i.e., the system is considered as a black box. Therefore, a network DEA (NDEA) is needed to study the internal structure of a system. By allowing for the measurement of individual components, an NDEA model can reveal inefficiencies that a traditional DEA ignores. In this study, we use the parallel network DEA to calculate the efficiency of a higher education institute with 19 decision-making units (DMUs) using two parallel processes (teaching and research) and compare it with the conventional DEA, CCR model through a numerical example. The main advantages of the parallel NDEA model are (i) to identify which DMUs are inefficient and make necessary adjustments, and (ii) the parallel DEA model has a lower efficiency score than the traditional DEA model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

DPT‐tracker:Dual pooling transformer for efficient visual tracking

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

来源：评论

学校读者我要写书评

暂无评论

Automated face recognition using deep learning technique and center symmetric multivariant local binary pattern

引用

Neural computing and Applications 2025年第1期37卷 263-281页

作者： Sekhar, J.C. Josephson, P. Joel Chinnasamy, A. Maheswari, M. Sankar, S. Kalangi, Ruth Ramya Department of Computer Science and Engineering NRI Institute of Technology Andhra Pradesh Guntur India Department of Electronics and Communication Engineering Malla Reddy Engineering College Telangana Hyderabad India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vijayawada India

Researchers have recently created several deep learning strategies for various tasks, and facial recognition has made remarkable progress in employing these techniques. Face recognition is a noncontact, nonobligatory, acceptable, and harmonious biometric recognition method with a promising national and social security future. The purpose of this paper is to improve the existing face recognition algorithm, investigate extensive data-driven face recognition methods, and propose a unique automated face recognition methodology based on generative adversarial networks (GANs) and the center symmetric multivariable local binary pattern (CS-MLBP). To begin, this paper employs the center symmetric multivariant local binary pattern (CS-MLBP) algorithm to extract the texture features of the face, addressing the issue that C2DPCA (column-based two-dimensional principle component analysis) does an excellent job of removing the global characteristics of the face but struggles to process the local features of the face under large samples. The extracted texture features are combined with the international features retrieved using C2DPCA to generate a multifeatured face. The proposed method, GAN-CS-MLBP, syndicates the power of GAN with the robustness of CS-MLBP, resulting in an accurate and efficient face recognition system. Deep learning algorithms, mainly neural networks, automatically extract discriminative properties from facial images. The learned features capture low-level information and high-level meanings, permitting the model to distinguish among dissimilar persons more successfully. To assess the proposed technique’s GAN-CS-MLBP performance, extensive experiments are performed on benchmark face recognition datasets such as LFW, YTF, and CASIA-WebFace. Giving to the findings, our method exceeds state-of-the-art facial recognition systems in terms of recognition accuracy and resilience. The proposed automatic face recognition system GAN-CS-MLBP provides a solid basis for a

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Indian States and Union Territories for Covid-19 Management Through DEA and Machine Learning 12th

Performance Analysis of Indian States and Union Territories ...

引用

12th International Conference on Soft computing for Problem Solving, SocProS 2023

作者： Joshi, Shubham Panwar, Ankita Pant, Millie Deep, Kusum Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Uttarakhand Roorkee247667 India Department of Mathematics Indian Institute of Technology Uttarakhand Roorkee247667 India Mehta Family School for Data Science and Artificial Intelligence Indian Institute of Technology Uttarakhand Roorkee247667 India

ISBN: (纸本)9789819731794

In this study, an analysis has been performed to assess the performance of 28 states and 8 union territories (UTs) of India against COVID-19 during the years 2020 and 2021. The study is done in three phases;first of all, the analysis has been done through Exploratory data Analysis (EDA), to get general information about the data;in the second phase, the super-efficiency-data envelopment analysis (SE-DEA) model has been applied to evaluate the performance of states and UTs, and to segregate them into two classes: efficient and inefficient. Finally, in the third phase, an attempt is made to establish a link between the DEA and 5 supervised machine learning techniques viz. Logistic regression (LR), K-nearest neighbours (KNN), Support vector machine (SVM), Naïve Bayes (NB) classifier, and Decision tree (DT) for analysis of the results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19

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：