检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Chen, Xiaoyu Hu, Jiachen Yang, Lin F. Wang, Liwei Key Laboratory of Machine Perception MOE School of Artificial Intelligence Peking University China Electrical and Computer Engineering Department University of California Los Angeles United States International Center for Machine Learning Research Peking University China

Although model-based reinforcement learning (RL) approaches are considered more sample efficient, existing algorithms are usually relying on sophisticated planning algorithm to couple tightly with the model-learning procedure. Hence the learned models may lack the ability of being re-used with more specialized planners. In this paper we address this issue and provide approaches to learn an RL model efficiently without the guidance of a reward signal. In particular, we take a plug-in solver approach, where we focus on learning a model in the exploration phase and demand that any planning algorithm on the learned model can give a near-optimal policy. specifically, we focus on the linear mixture MDP setting, where the probability transition matrix is a (unknown) convex combination of a set of existingmodels. We show that, by establishing a novel exploration algorithm, the plug-in approach learns a model by taking O(d2H3/ϵ2) episodes with the environment and any ϵ-optimal planner on the model gives an O(ϵ)-optimal policy on the original model. This sample complexity matches our lower bound for non-plug-in approaches and is statistically optimal. We achieve this result by leveraging a careful maximum total-variance bound using Bernstein inequality and properties specified to linear mixture MDPs. Copyright © 2021, The Authors. All rights reserved.

关键词： Mixtures

来源：评论

学校读者我要写书评

暂无评论

Early Detecting the At-risk Students in Online Courses Based on Their Behavior Sequences 10th

Early Detecting the At-risk Students in Online Courses Based...

引用

10th EAI International Conference on Big Data Technologies and Applications, BDTA 2020 and 13th EAI International Conference on Wireless Internet, WiCON 2020

作者： Yuan, Shuai Huang, Huan He, Tingting Hou, Rui National Engineering Research Center for E-Learning Central China Normal University Wuhan China School of Education South-Central University for Nationalities Wuhan China Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer National Language Resources Monitoring & Research Center for Network Media Central China Normal University Wuhan China College of Computer Science South-Central University for Nationalities Wuhan China

ISBN: (纸本)9783030728014

Online learning has developed rapidly, but the participation of learners is very low. So it is of great significance to construct a prediction model of learning results, to identify students at risk in time and accurately. We select nine online learning behaviors from one course in Moodle, take one week as the basic unit and 5 weeks as the time node of learning behavior, and the aggregate data and sequence data of the first 5 weeks, the first 10 weeks, the first 15 weeks, the first 20 weeks, the first 25 weeks, the first 30 weeks, the first 35 weeks and the first 39 weeks are formed. Eight classic machine learning methods, i.e. Logistic Regression (LR), Naive Bayes (NB), Radom Forest (RF), K-Nearest Neighbors (KNN), Support Vector machine (SVM), Iterative Dichotomiser3 (ID3), Classification and Regression Trees (CART), and Neural Network (NN), are used to predict the learning results in different time nodes based on aggregate data and sequence data. The experimental results show that sequence data is more effective than aggregate data to predict learning results. The prediction AUC of RF model on sequence data is 0.77 at the lowest and 0.83 at the highest, the prediction AUC of CART model on sequence data is 0.70 at the lowest and 0.83 at the highest, which are the best models of the eight classic prediction models. Then Radom Forest (RF) model, Classification and Regression Trees (CART) model, recurrent neural network (RNN) model and long short term memory (LSTM) model are used to predict learning results on sequence data;the experimental results show that long short term memory (LSTM) is a model with the highest value of AUC and stable growth based on sequence data, and it is the best model of all models for predicting learning results. © 2021, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optical Character Recognition (OCR) in Handwritten Characters Using Convolutional Neural Networks to Assist in Exam Reader System

Optical Character Recognition (OCR) in Handwritten Character...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： P L Lekshmy S. Velmurugan Indra Kumari S. Kayalvili B. Teja Sree P. Karthik Kumar Department of Computer Science and Engineering LBS Institute of Technology for Women Kerala India Department of Electronics and Communication Engineering T.J.S. Engineering College Chennai Tamil Nadu India Department of Machine Learning Data Research Applied AI Korea National University of Science and Technology (UST) Daejeon South Korea Department of Artificial Intelligence Kongu Engineering College (Autonomous) Erode Tamilnadu India Department of Information Technology S.R.K.R. Engineering College Chinaamiram Bhimavaram Andhra Pradesh India Department of Computer Science and Engineering (Cyber Security) Karpagam College of Engineering Coimbatore India

ISBN: (数字)9798350371314

ISBN: (纸本)9798350371321

This work aimed to develop a character recognition method to facilitate the correction of answer cards in the Multiprova software through the development of a response card analysis flow that would culminate in the recognition of letters written by students and automatic correction of the tests. To isolate and identify the answers written on the answer cards, image segmentation techniques were used based on fixed marks printed on the cards. To recognize the letters and numbers written on the cards, trained three convolutional neural networks (for digits, letters and true or false). The results achieved (98.84% accuracy for digit CNN, 98.38% accuracy for letter CNN and 99.89% accuracy for true or false CNN) point out a great average success rate.

关键词： Training Image segmentation Image recognition Codes Optical character recognition Neural networks Streaming media

来源：评论

学校读者我要写书评

暂无评论

Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification

arXiv

引用

arXiv 2022年

作者： Wu, Chao Ge, Wenhang Wu, Ancong Chang, Xiaobin School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China School of Computer Science and Engineering Sun Yat-sen University China

To learn camera-view invariant features for person Re-IDentification (Re-ID), the cross-camera image pairs of each person play an important role. However, such cross-view training samples could be unavailable under the ISolated Camera Supervised (ISCS) setting, e.g., a surveillance system deployed across distant scenes. To handle this challenging problem, a new pipeline is introduced by synthesizing the cross-camera samples in the feature space for model training. Specifically, the feature encoder and generator are end-to-end optimized under a novel method, Camera-Conditioned Stable Feature Generation (CCSFG). Its joint learning procedure raises concern on the stability of generative model training. Therefore, a new feature generator, σ-Regularized Conditional Variational Autoencoder (σReg. CVAE), is proposed with theoretical and experimental analysis on its robustness. Extensive experiments on two ISCS person Re-ID datasets demonstrate the superiority of our CCSFG to the competitors. 1 © 2022, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

ESVAE: An Efficient Spiking Variational Autoencoder with Reparameterizable Poisson Spiking Sampling

arXiv

引用

arXiv 2023年

作者： Zhan, Qiugang Tao, Ran Xie, Xiurui Liu, Guisong Zhang, Malu Tang, Huajin Yang, Yang The Complex Laboratory of New Finance and Economics School of Computing and Artificial Intelligence Southwestern University of Finance and Economics Chengdu611130 China The Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China Chengdu611731 China The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China The College of Computer Science The State Key Laboratory of Brain-Machine Intelligence Zhejiang University Hangzhou310027 China

In recent years, studies on image generation models of spiking neural networks (SNNs) have gained the attention of many researchers. Variational autoencoders (VAEs), as one of the most popular image generation models, have attracted a lot of work exploring their SNN implementation. Due to the constrained binary representation in SNNs, existing SNN VAE methods implicitly construct the latent space by an elaborated autoregressive network and use the network outputs as the sampling variables. However, this unspecified implicit representation of the latent space will increase the difficulty of generating high-quality images and introduce additional network parameters. In this paper, we propose an efficient spiking variational autoencoder (ESVAE) that constructs an interpretable latent space distribution and designs a reparameterizable spiking sampling method. Specifically, we construct the prior and posterior of the latent space as a Poisson distribution using the firing rate of the spiking neurons. Subsequently, we propose a reparameterizable Poisson spiking sampling method, which is free from the additional network. Comprehensive experiments have been conducted, and the experimental results show that the proposed ESVAE outperforms previous SNN VAE methods in reconstructed & generated image quality. In addition, experiments demonstrate that the encoder of ESVAE can retain the original image information more efficiently and is more robust. The source code is available at https://***/QgZhan/ESVAE. Copyright © 2023, The Authors. All rights reserved.

关键词： Poisson distribution

来源：评论

学校读者我要写书评

暂无评论

A CNN Approach To Detect Vanishing Point By Considering Street Lane

A CNN Approach To Detect Vanishing Point By Considering Stre...

引用

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： A Shruthiba R Deepu Amit Dhomne Artificial Intelligence and Machine Learning Bangalore Institute of Technology Bengaluru India ATME College of Engineering Computer Science and Engineering Mysuru India CSE NIT Rourkela Rourkela Odisha India

ISBN: (纸本)9781665406116

Linear perspective is widely used in highway road images to create the impression of depth on 2D/3D photos and detect vanishing points with the help of parallel lanes lines on road images. Automated understanding of linear perspective in landscape, road, street photo collections video has a number of real-world applications. This problem of automated understanding of linear perspective in images is addressed with the help of hough transform and CNN framework architecture to detect vanishing points. However, images of the road taken from street and highway video pose a very great technical challenge, because an insufficient number of parallel edges or lines intersect and lead to false vanishing points. To solve this problem, a state of art vanishing point detection method is proposed that exploits the vanishing point and intersection of parallel lines with the help of possible parallel lines to lane lines available in the image, the center of origin, and quadrant. The proposed strategy essentially performs best in detecting vanishing points on a public road image data set.

关键词： Roads Image edge detection Conferences Neural networks Estimation Transforms computer architecture

来源：评论

学校读者我要写书评

暂无评论

Wireless Capsule Endoscopy for Crohn's Disease Automated Image Classification Using Deep learning

Wireless Capsule Endoscopy for Crohn's Disease Automated Ima...

引用

Integrated intelligence and Communication Systems (ICIICS), International Conference on

作者： P. Nalayini S. Jayasankari C. Gunasundari G. Elumalai Bharathi Ramesh Kumar E Balamurugan School of Computing Sastra Deemed to be University Thanjavur India School of Computing/CSE Sastra Deemed to be University Thanjavur India School of Computing SRM Institute of Science and Technology Tiruchirappalli India Department of ECE Panimalar Engineering College Chennai India Department of Mathematics Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Artificial intelligence and Machine Learning Bannari Amman Institute of Technology Sathyamangalam India

ISBN: (数字)9798331504960

ISBN: (纸本)9798331504977

Despite the diagnosis of Crohn's Disease now transformed through wireless capsule endoscopy (WCE), traditional manual interpretation by gastroenterologists contains substantial restrictions such as high inter-observer inconsistency, time dedication, and potential oversight of important clinical signs. The paper proposes an automated image classification system founded on deep learning methods specifically, Convolutional Neural Network (CNN) for feature extraction and Long Short-Term Memory networks (LSTM) for temporal sequence examination. The technique applies Transfer learning to improve model performance with minimal labeled data, thus facilitating precise identification of CD-related abnormalities. Strong testing on an endoscopist-annotated dataset indicates the proposed system substantially surpasses existing systems about accuracy of 94.5%, sensitivity of 92.0%, and specificity of 96.0%. Promising enhanced patient outcomes in the therapy of Crohn's Disease, the automated method significantly decreases interpretation time, minimizes inter-observer inconsistency, and increases diagnostic accuracy.

关键词： Wireless communication Deep learning Wireless sensor networks Accuracy Endoscopes Crohn's disease Gastrointestinal tract Medical diagnostic imaging Long short term memory Image classification

来源：评论

学校读者我要写书评

暂无评论

XAI for Transformers: Better Explanations through Conservative Propagation

arXiv

引用

arXiv 2022年

作者： Ali, Ameen Ali Schnake, Thomas Eberle, Oliver Montavon, Grégoire Müller, Klaus-Robert Wolf, Lior The School of Computer Science Tel-Aviv University Israel Machine Learning Group Technische Universität Berlin Berlin Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin Germany Department of Artificial Intelligence Korea University Seoul Korea Republic of Max Planck Institute for Informatics Saarbrücken Germany

Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on gradient information, have been proposed. We show that the gradient in a Transformer reflects the function only locally, and thus fails to reliably identify the contribution of input features to the prediction. We identify Attention Heads and LayerNorm as the main reasons for such unreliable explanations and propose a more stable way for propagation through these layers. Our proposal, which can be seen as a proper extension of the well-established LRP method to Transformers, is shown both theoretically and empirically to overcome the deficiency of a simple gradient-based approach, and achieves state-of-the-art explanation performance on a broad range of Transformer models and datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Big Data Analytics with Wild Horse Optimizer based Deep learning Model for Healthcare Management

Big Data Analytics with Wild Horse Optimizer based Deep Lear...

引用

International Conference on Inventive Research in Computing Applications (ICIRCA)

作者： M. Vamsikrishna Rajasree RS Gopika G S D. Suganthi Md. Abul Ala Walid Ramu Kuchipudi Department of Information Technology Aditya Engineering College (A) Surampalem Andhra Pradesh India Department of Artificial Intelligence & Machine Learning New Horizon College of Engineering Bangalore Karnataka India Department of Computer Science Sathyabama Institute of Science and Technology Chennai Tamilnadu India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Chennai Tamilnadu India Department of Computer Science and Engineering Khulna University of Engineering & Technology (KUET) Khulna Department of Information Technology Chaitanya Bharathi Institute of Technology Hyderabad Telangana India

Big data analytics in health service is the procedure of research in huge and different datasets, designed for uncovering hidden patterns, correlations, and trends for making the best decisions in medical field. The health and medical services are developed modern and smart healthcare platforms are made the analysis further robust for the treatment. The proper diagnosis of health records depends on primarily disease recognition and the value of accuracy is decreased if the clinical data quality is worse. But, the existing methods failed to use the learning model for handling heterogeneous healthcare information. Therefore, this article introduces Big Data Analytics with Wild Horse Optimizer based deep learning (BDAWHO-DL) model for Healthcare Management. The proposed BDAWHO-DL technique investigates the big data in medical field and makes decisions. To do so, the BDAWHO-DL technique exploits attention based long short term memory (ABLSTM) method for data classification purposes. Moreover, the WHO system was used for the optimal hyperparameter tuning procedure of the ABLSTM algorithm to boost the classifier outcomes. The experimental outcomes indicate the promising outcomes of the BDAWHO-DL algorithm over recent approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Industrial Quality Control with computer Vision and Deep learning

Anomaly Detection in Industrial Quality Control with Compute...

引用

Distributed Systems, computer Networks and Cybersecurity (ICDSCNC), International Conference on

作者： A. Jenita Mary V. Umesh Prerana Nilesh Khairnar R Sahana Sangeethaa SN Shanthi H J Department of Computer Science and Applications SRM Institute of Science and Technology Faculty of Science and Humanities Vadapalani City Campus Chennai India Department of IT Ksou Mysore Mysuru India Department of Electronics and Telecommunication Engineering Visvesvaraya Institute of Technology Chincholi Nashik India Department of Artificial Intelligence and Machine Learning Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Avadi Chennai India Department of Computer Science & Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Computer Applications Hindustan Institute of Technology and Science Deemed to be University Padur India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

This study examines the impact of the dynamic manufacturing environment on companies' efforts to improve customer satisfaction through product quality enhancement, production cost reduction, and sustainability realisation. The research focuses on the current trends and challenges companies face in adapting in response to the dynamic nature of the industrial industry. This study seeks to offer practical recommendations by analyzing these factors for companies to meet the evolving demands of their customers while ensuring long-term success and competitiveness. This study examines the impact of anomaly detection on product quality, specifically focusing on the commonly employed method of visual quality inspection. This study examines the methods of visual quality inspection for products, comparing manual and automatic approaches. This study examines the limitations of manual inspection as a monotonous task, which can result in the oversight of errors and subjective assessments. In order to keep up with the needs of smart production and the advent of Industry 4.0, manufacturing as a whole is actively seeking computerized quality inspection solutions. Innovative inspection systems can be created through the effective use of big data. This research abstract discusses the widespread use of machine learning in automated quality inspection systems to enhance performance and support data analytics methods. This study uses a convolutional neural network architecture to extract complex features and patterns from images. This enables the model to differentiate between normal and abnormal conditions effectively. This research presents a proposed model trained on a diverse dataset, including a comprehensive collection of potential defects and irregularities. This research abstract presents a proposed framework for validating effectiveness through extensive experiments on datasets from diverse industrial domains. This study presents the findings of a research project that evaluated

关键词： Training Deep learning Adaptation models Accuracy Computational modeling Quality control Production Inspection Convolutional neural networks Anomaly detection

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：