检索结果-内蒙古大学图书馆

23rd IEEE International Conference on data Mining, ICDM 2023

作者： Nguyen, Ngoc Dang Tan, Wei Du, Lan Buntine, Wray Beare, Richard Chen, Changyou Monash University Department of Data Science and Ai Melbourne Australia VinUniversity College of Engineering and Computer Science Hanoi Viet Nam Faculty of Medicine Peninsula Clinical School Melbourne Australia University at Buffalo Department of Cs and Engineering New York United States

ISBN: (纸本)9798350307887

Named entity recognition (NER), a task that identifies and categorizes named entities such as persons or organizations from text, is traditionally framed as a multi-class classification problem. However, this approach often overlooks the issues of imbalanced label distributions, particularly in low-resource settings, which is common in certain NER contexts, like biomedical NER (bioNER). To address these issues, we propose an innovative reformulation of the multi-class problem as a one-vs-all (OVA) learning problem and introduce a loss function based on the area under the receiver operating characteristic curve (AUC). To enhance the efficiency of our OVA-based approach, we propose two training strategies: one groups labels with similar linguistic characteristics, and another employs meta-learning. The superiority of our approach is confirmed by its performance, which surpasses traditional NER learning in varying NER settings. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

OVER-PARAMETERIZED MODEL OPTIMIZATION WITH POLYAK-LOJASIEWICZ CONDITION

OVER-PARAMETERIZED MODEL OPTIMIZATION WITH POLYAK-LOJASIEWIC...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Chen, Yixuan Shi, Yubin Dong, Mingzhi Yang, Xiaochen Li, Dongsheng Wang, Yujiang Dick, Robert P. Lv, Qin Zhao, Yingying Yang, Fan Gu, Ning Shang, Li China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China School of Mathematics Statistics The University of Glasgow Glasgow United Kingdom Microsoft Research Asia Shanghai China Department of Engineering Science University of Oxford Oxford United Kingdom Department of Electrical Engineering and Computer Science University of Michigan Michigan United States Department of Computer Science University of Colorado Boulder BoulderCO United States School of Microelectronics Fudan University Shanghai China

This work pursues the optimization of over-parameterized deep models for superior training efficiency and test performance. We first theoretically emphasize the importance of two properties of over-parameterized models, i.e., the convergence gap and the generalization gap. Subsequent analyses unveil that these two gaps can be upper-bounded by the ratio of the Lipschitz constant and the Polyak-Lojasiewicz (PL) constant, a crucial term abbreviated as the condition number. Such discoveries have led to a structured pruning method with a novel pruning criterion. That is, we devise a gating network that dynamically detects and masks out those poorly-behaved nodes of a deep model during the training session. To this end, this gating network is learned via minimizing the condition number of the target model, and this process can be implemented as an extra regularization loss term. Experimental studies demonstrate that the proposed method outperforms the baselines in terms of both training efficiency and test performance, exhibiting the potential of generalizing to a variety of deep network architectures and tasks. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Design of Chatbot to Prevent Cyberbullying from Social Media

Design of Chatbot to Prevent Cyberbullying from Social Media

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Erin Sanu Medha Mummigatti Mohana Computer Science and Engineering (Data Science) RV College of Engineering® Bengaluru India Computer Science and Engineering (Cyber Security) RV College of Engineering® Bengaluru India

In the present world, social media has greatly influenced our lives but with the increase in usage of social media, people get exposed to its adverse impacts as well. The common and major impact is cyberbullying, which tends to have tremendous negative impacts on the victim's life. Hence, detecting cyberbullying has now become a crucial task. This research study proposes a novel chatbot design to identify the occurrences of cyberbullying based on user's input and provide emotive support or guidance as required. It also offers data on various aspects and domains of cyberbullying, thus helping to create a safer online environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Stacking-Based Deep Neural Network Approach for Effective Network Anomaly Detection

引用

computers, Materials & Continua 2021年第2期66卷 2217-2227页

作者： Lewis Nkenyereye Bayu Adhi Tama Sunghoon Lim Department of Computer and Information Security Sejong UniversitySeoul05006Korea Data Science Group Institute for Basic Science(IBS)Daejeon34126Korea Department of Industrial Engineering Ulsan National Institute of Science and TechnologyUlsan44919Korea

An anomaly-based intrusion detection system(A-IDS)provides a critical aspect in a modern computing infrastructure since new types of attacks can be *** prevalently utilizes several machine learning algorithms(ML)for detecting and classifying network *** date,lots of algorithms have been proposed to improve the detection performance of A-IDS,either using individual or ensemble *** particular,ensemble learners have shown remarkable performance over individual learners in many applications,including in cybersecurity ***,most existing works still suffer from unsatisfactory results due to improper ensemble *** aim of this study is to emphasize the effectiveness of stacking ensemble-based model for A-IDS,where deep learning(e.g.,deep neural network[DNN])is used as base learner *** effectiveness of the proposed model and base DNN model are benchmarked empirically in terms of several performance metrics,i.e.,Matthew’s correlation coefficient,accuracy,and false alarm *** results indicate that the proposed model is superior to the base DNN model as well as other existing ML algorithms found in the literature.

关键词： Anomaly detection deep neural network intrusion detection system stacking ensemble

来源：评论

学校读者我要写书评

暂无评论

Handling of Simultaneous Morphology of Sign Languages: Concerns for Cross-modal Machine Translation of Marathi to Indian Sign Language

引用

SN computer science 2023年第5期4卷 629页

作者： Bhagwat, Suvarna R. Bhavsar, R.P. Pawar, B.V. Department of Artificial Intelligence and Data Science Vishwakarma Institute of Information Technology Maharashtra Pune 411037 India School of Computer Sciences KBC North Maharashtra University Umavi Nagar Maharashtra Jalgaon 425001 India

Effective communication can be challenging when individuals are unfamiliar with each other's spoken language. This problem becomes more complex when the languages involved differ in modality such as spoken language and sign language. Machine translation has emerged as a valuable tool for bridging this communication gap in various scenarios. This research addresses the unique challenges presented by cross-modal machine translation systems, specifically in translating from spoken language to sign language. While spoken languages typically exhibit linear linguistic characteristics, sign languages employ simultaneous expressions through manual, non-manual, and spatial features. This divergence in delivery mechanisms necessitates careful consideration in the development of a translation system. The primary objective of this research is to develop a framework that translates simple Marathi sentences into Indian sign language, incorporating computational techniques to account for the simultaneous nature of sign language grammar. A comprehensive linguistic analysis is conducted to identify the specific divergences between Marathi and Indian sign language. The system is evaluated using a database comprising vocabulary relevant to daily communication. This paper provides a detailed account of the system architecture, experimental setup, results, and evaluation. The development of a cross-modal translation system holds significant potential in bridging the communication gap between individuals using spoken languages and those who rely on sign languages as their primary means of communication. The system-generated ISL can facilitate communication for hearing-impaired persons and, thus, it contributes to the inclusivity of hearing-impaired communities in the mainstream. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cross-modal machine translation Inclusion of hearing-impaired people Indian sign language Marathi Phrase-based machine translation Simultaneous morphology

来源：评论

学校读者我要写书评

暂无评论

Toward Large Kernel Models

arXiv

引用

arXiv 2023年

作者： Abedsoltan, Amirhesam Belkin, Mikhail Pandit, Parthe Department of Computer Science and Engineering Halicioglu Data Science Institute UC San Diego United States

Recent studies indicate that kernel machines can often perform similarly or better than deep neural networks (DNNs) on small datasets. The interest in kernel machines has been additionally bolstered by the discovery of their equivalence to wide neural networks in certain regimes. However, a key feature of DNNs is their ability to scale the model size and training data size independently, whereas in traditional kernel machines model size is tied to data size. Because of this coupling, scaling kernel machines to large data has been computationally challenging. In this paper, we provide a way forward for constructing large-scale general kernel models, which are a generalization of kernel machines that decouples the model and data, allowing training on large datasets. Specifically, we introduce EigenPro 3.0, an algorithm based on projected dual preconditioned SGD and show scaling to model and data sizes which have not been possible with existing kernel methods. We provide a PyTorch based implementation which can take advantage of multiple GPUs. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Prior Information Guided Semi-Supervised Semantic Segmentation of Remote Sensing Images

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Gan, Xiaorong Li, Wenting Zhang, Yongjun Long, Wei Lu, Yujie Chen, Ziyang Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou Guiyang550025 China University of Electronic Science and Technology of China School of Computer Science and Engineering College Chengdu611731 China Guizhou University of Commerce School of Computer and Information Engineering College Guizhou Guiyang550014 China

Remote sensing semantic segmentation has broad applications in critical fields such as urban planning and environmental monitoring. Semi-supervised semantic segmentation methods tackle the time and cost challenges of annotating remote sensing images by using abundant unlabeled data to optimize the model. Many existing semi-supervised methods generate pseudo-labels by inputting unlabeled data into the network, and then use these labels to progressively improve the model’s segmentation performance. However, the imbalanced class distribution and complex spatial layout of remote sensing images may result in unreliable pseudo-labels generated by the networks. To address this issue, we propose a Prior Information Guided Network (PGNet) that integrates a Prior Feature Guided Module (PFGM) for reliable feature priors and a Prior Edge Extraction Module (PEEM) to provide edge prior information. By leveraging the lightweight Segment Anything Model (SAM), PGNet enhances the ability to extract valuable information from unlabeled data, enabling the generation of more reliable pseudo-label. The PFGM employs Symmetric Cross-Attention to more balancedly integrate the SAM prior features with the semantic features from the encoder. Additionally, the PEEM employs SAM to extract reliable edge priors from unlabeled data, guiding the feature maps during training for more accurate segmentation boundaries. We conducted extensive experiments on the ISPRS Vaihingen, ISPRS Potsdam, and LoveDA datasets. The results demonstrate that our PGNet outperforms existing state-of-the-art semi-supervised methods. © 1980-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Mental Workload Classification from fNIRS Signals by Leveraging Machine Learning

Mental Workload Classification from fNIRS Signals by Leverag...

引用

2023 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2023

作者： Hasan, M. Mahmud, M. Poudel, S. Donthula, K. Poudel, K. University of Memphis Department of Electrical and Computer Engineering TN United States Senior Software Engineer Optum Inc MurfreesboroTN United States Middle Tennessee State University Computational and Data Science MurfreesboroTN United States Middle Tennessee State University Computer Science MurfreesboroTN United States

ISBN: (纸本)9798350341256

Mental workload (MWL) identification is vital to know human cognitive functioning, performance, and well-being. In this work, we develop models for identifying low vs. high MWL using different genres of machine learning classifiers. We used non-invasive functional near-infrared spectroscopy (fNIRS) signals while participants classified the low vs. high levels of MWL tasks. Our analysis shows the low vs. high MWL can be identified best from the whole brain data. The k-nearest neighbors classifier showed the best performance with an accuracy of 98.8%, an area under the curve (AUC) of 98.8%, F1 score, precision, and recall of 98.0% from the whole brain data without overlapping signals. A separate hemisphere analysis using left hemisphere (LH) and right hemisphere (RH) activity showed that the LH activity has better classification ability than the RH activity. We also examined the classification with the top six features that could identify the low vs. high MWL with an accuracy of 97.4%, (AUC) 97.4%, F1 score, precision, and recall of 97.0%. These findings would be useful for developing more intuitive and user-friendly interfaces in the human-computer interface. © 2023 IEEE.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Classification of Real and Deepfakes Visual Samples with Pre-trained Deep Learning Models 7th

Classification of Real and Deepfakes Visual Samples with Pre...

引用

Proceedings of the 7th International Conference on Advances in Computing and data sciences, ICACDS 2023

作者： Nawaz, Marriam Javed, Ali Nazir, Tahira Khan, Muhammad Attique Rajinikanth, Venkatesan Kadry, Seifedine Department of Software Engineering UET Taxila Taxila47050 Pakistan Department of Computing Riphah International University Islamabad Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Department of Applied Data Science Noroff University College Kristiansand4612 Norway Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9783031379390

Serious security and privacy problems have arisen as a result of significant advancements in the creation of deepfakes. Attackers can easily replace a person’s face with the target person’s face in an image using sophisticated Deep learning (DL) algorithms to spoof their identity. Deepfakes detection algorithms have been proposed in response to the growing concerns about the potential harm caused by deepfakes. However, a reliable deepfakes detector that can keep up with contemporary deepfakes creation techniques is required. In this work, we have proposed an end-to-end methodology for detecting manipulated visual content. We used multiple CNN models i.e., ResNet18, ResNet50, DenseNet65, DenseNet77, and DenseNet100 along with the SVM classifier to compute effective cues from the input facial faces to distinguish between actual and altered content. We have also applied the concept of transfer learning to solve the issue of model over-fitting and improve generalizability against different manipulation algorithms. A comparison study is carried out to evaluate the performance of several feature extractors. Through thorough experiments performed using the Deepfakes Detection Challenge dataset, our results demonstrated that DenseNet100 surpasses the other CNN models by better recognizing deepfakes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Protein Generation via Genome-scale Language Models with Bio-physical Scoring

Protein Generation via Genome-scale Language Models with Bio...

引用

2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023

作者： Dharuman, Gautham Ward, Logan Ma, Heng Setty, Priyanka V. Gokdemir, Ozan Foreman, Sam Emani, Murali Hippe, Kyle Brace, Alexander Keipert, Kristopher Gibbs, Thomas Foster, Ian Anandkumar, Anima Vishwanath, Venkatram Ramanathan, Arvind Data Science and Learning Division United States Argonne Leadership Computing Facility Argonne National Laboratory United States Computer Science Department University of Chicago United States Nvidia Inc. United States California Institute of Technology United States

ISBN: (纸本)9798400707858

Large language models (LLMs) trained on vast biological datasets can learn biological motifs and correlations across the evolutionary landscape of natural proteins. LLMs can then be used for de novo design of novel proteins with specific structures, functions, and physicochemical properties. We employ a pre-trained genome-scale language model that uses codons as tokens and integrate it into a workflow for targeted generation of sequences. Our framework suggests new gene sequences that are ranked for downstream evaluation by metrics that collectively capture extensive sequence-specific, biophysical, and biochemical properties. We demonstrate our integrated workflow to design novel variants of the enzyme, malate dehydrogenase (MDH), that exhibit more favorable activation energies than their natural counterparts (reduction of 4.01 kJ/mol) with sustained sequence generation rates of ~104/hr and simulation rates of ~102/hr on 64 nodes of Polaris with about 99.7 system utilization during the run. © 2023 ACM.

关键词： Physicochemical properties

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：