检索结果-内蒙古大学图书馆

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Zhou, Hang Wang, Chenglong Hu, Yimin Xiao, Tong Zhang, Chunliang Zhu, Jingbo NLP Lab School of Computer Science and Engineering Northeastern University Shenyang China NiuTrans Research Shenyang China

ISBN: (纸本)9789819783663

Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs. However, the training procedure suffers from an inherent problem: the uncontrolled scaling of reward scores during reinforcement learning due to the lack of constraints while training the reward model. This paper proposes a Prior Constraints-based Reward Model (PCRM) training method to mitigate this problem. PCRM incorporates prior constraints-specifically, length ratio and cosine similarity between outputs of each comparison pair-during reward model training to regulate optimization magnitude and control score margins. We comprehensively evaluate PCRM by examining its rank correlation with human preferences and its effectiveness in aligning LLMs via RL. Experimental results demonstrate that PCRM significantly improves alignment performance by effectively constraining reward score scaling. As another bonus, our method is easily integrated into arbitrary rank-based alignment methods, such as direct preference optimization, and can yield consistent improvement. The code is available at https://***/wangclnlp/DeepSpeed-Chat-Extension/tree/PCRM. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

LesNet: An Automated Skin Lesion Deep Convolutional Neural Network Classifier through Augmentation and Transfer Learning 2

LesNet: An Automated Skin Lesion Deep Convolutional Neural N...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Mir, Aqib Nazir Nissar, Iqra Rizvi, Danish Raza Kumar, Ankush Research Lab Department of Computer Engineering Jamia Millia Islamia New Delhi110025 India Department of Computer Science and Engineering Punjabi University Punjab 147002 India

Skin cancer is one of the most prevalent forms of cancer around the world. Initial diagnosis relies on visual assessment of the affected area, followed by detailed dermoscopic analysis. The development of an automated system for classifying skin lesions poses a considerable challenge due to inherent noise and subtle variability in lesion images. Deep convolutional neural networks have demonstrated exceptional proficiency in image classification tasks spanning diverse domains. This paper demonstrates an end-to-end classification architecture built on top of transfer learning with data augmentation. The proposed model capitalizes on pre-trained architectures such as DenseNet, VGG-16, and Inception for feature extraction, and employs fully connected dense layers for categorizing seven distinct types of lesions. Several data augmentation techniques are also used to handle the class imbalance problem. Extensive experimentation encompassing various hyperparameters, imbalanced data scenarios, and balanced datasets was conducted to refine the automated skin lesion system. The proposed approach achieved a notable accuracy of 98% on the HAM10000 dataset and 94% on the ISIC-2019 dataset. Importantly, the experimental findings surpassed the performance of current state-of-the-art models for lesion classification. Furthermore, this paper examines the impact of class imbalance and data augmentation on the model's accuracy. © 2024 Elsevier B.V.. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Unleashing Future Donors Navigating Blood Contribution Propensity with Machine Learning Expertise 1

Unleashing Future Donors Navigating Blood Contribution Prope...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Dhami, Kavindra Singh Gusain, Raj Shekhar, Sushant Vidyarth, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Civil Engineering Dehradun India Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350377002

The study used machine learning techniques, which are an essential component of blood donation and health care. Data details of blood donation and service centers have been included in this study. Some of these variables include the number of times a person donates, the frequency of donations, and the time since the last donation. Modern technology machine learning methods analyze and consider key factors in the model. This is valuable information for physicians and blood transfusion centers because here we can predict when a donor may be able to donate blood again. Furthermore, our study aims to examine not only donor behavior but also whether blood donation will provide a continued flow of blood products to health systems in the future. The study of blood donation system is enhanced by this analysis method, which also provides an indication to take care of the health care of the society. We have taken our extensive analysis into account and used cross-validation and performance F1 scores. Donor confidentiality, equity and ethics are equally important to us in the development of our studies. Our approach can play an important role in the technological development sector. Our aim is to draw attention to how donor contact strategies will work, and to improve this, with a view to making the blood supply more reliable. © 2024 IEEE.

关键词： Blood Donation Donor Propensity Healthcare Optimization Machine Learning Stable Blood Supply

来源：评论

学校读者我要写书评

暂无评论

XGCN:a library for large-scale graph neural network recommendations

引用

Frontiers of computer Science 2024年第3期18卷 247-249页

作者： Xiran SONG Hong HUANG Jianxun LIAN Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Microsoft Research Asia Beijing 100080China

1 Introduction Graph Neural Networks(GNNs)have gained widespread adoption in recommendation systems,and nowadays there is a pressing need to effectively manage large-scale graph data[1].When it comes to large graphs,GNNs may encounter the scalability issue stemming from their multi-layer messagepassing ***,scaling GNNs has emerged as a crucial research area in recent years,with numerous scaling strategies being proposed.

关键词： scaling gained operations

来源：评论

学校读者我要写书评

暂无评论

ReCSA:a dedicated sort accelerator using ReRAM-based content addressable memory

引用

Frontiers of computer Science 2023年第2期17卷 1-13页

作者： Huize LI Hai JIN Long ZHENG Yu HUANG Xiaofei LIAO National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

With the increasing amount of data,there is an urgent need for efficient sorting algorithms to process large data *** sorting algorithms have attracted much attention because they can take advantage of different hardware's *** the traditional hardware sort accelerators suffer“memory wall”problems since their multiple rounds of data transmission between the memory and the *** this paper,we utilize the in-situ processing ability of the ReRAM crossbar to design a new ReCAM array that can process the matrix-vector multiplication operation and the vector-scalar comparison in the same array *** this designed ReCAM array,we present ReCSA,which is the first dedicated ReCAM-based sort *** hardware designs,we also develop algorithms to maximize memory utilization and minimize memory exchanges to improve sorting *** sorting algorithm in ReCSA can process various data types,such as integer,float,double,and *** also present experiments to evaluate the performance and energy efficiency against the state-of-the-art sort *** experimental results show that ReCSA has 90.92×,46.13×,27.38×,84.57×,and 3.36×speedups against CPU-,GPU-,FPGA-,NDP-,and PIM-based platforms when processing numeric data *** also has 24.82×,32.94×,and 18.22×performance improvement when processing string data sets compared with CPU-,GPU-,and FPGA-based platforms.

关键词： ReCAM parallel sorting architecture design processing-in-memory

来源：评论

学校读者我要写书评

暂无评论

Sales Prediction in the Retail Industry Using Machine Learning: A Case Study of BigMart

Sales Prediction in the Retail Industry Using Machine Learni...

引用

2023 IEEE International Conference on Electrical, Electronics, Communication and computers, ELEXCOM 2023

作者： Upadhyay, Hrishabh Shekhar, Sushant Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Computer Science Engineering Dehradun India Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350305111

This research paper presents a machine learning-based approach for sales prediction in the retail industry. The study was conducted using data collected from the BigMart retail chain. The research aimed to develop an accurate predictive model to forecast different products' sales in various BigMart stores. The study involved the implementation of several machine learning algorithms, including linear regression, decision tree, random forest, gradient boosting, support vector machine, convolutional neural network, and long short-term memory. The models were trained and evaluated using a dataset comprising of over 8,000 entries of sales data from different BigMart stores. The results showed that the convolutional neural network and long short-term memory models outperformed the other algorithms in terms of accuracy, with an R-squared value of 0.68 and 0.69, respectively. The study also identified the most significant features affecting sales, including item weight, store location, and promotional activities. The findings of this research have significant implications for the retail industry, as accurate sales prediction can help businesses optimize their inventory management and marketing strategies. The study also highlights the potential of machine learning algorithms for sales forecasting in the retail sector. In conclusion, this research demonstrates the effectiveness of machine learning in predicting sales and highlights the importance of leveraging advanced analytical techniques for improving business performance in the retail industry. © 2023 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Novel add-drop filter based on serial and parallel photonic crystal ring resonators (PCRR)

引用

Journal of Optical Communications 2024年第2期45卷 235-247页

作者： Fakhruldeen, Hassan Falah Al-Asady, Heba Abdul-Jaleel Mahinroosta, Tayebeh Sohrabi, Foozieh Hamidi, Seyedeh Mehri Computer Techniques Engineering Department Faculty of Information Technology Imam Ja’afar Al-sadiq University Baghdad Iraq Electrical Engineering Department College of Engineering University of Kufa Kufa Iraq Computer Technical Engineering Department College of Technical Engineering The Islamic University Najaf Iraq Magneto-Plasmonic Lab Laser and Plasma Research Institute Shahid Beheshti University Tehran*** Iran

Photonic crystal ring resonators (PCRR) as momentous candidates for future photonic crystal integrated circuits (PCICs) draw worldwide attention. In this paper, different configurations are proposed based on single, parallel, and serial PCRRs. To be precise, the different coupling lengths and alignments have been discussed in double and triple PCRRs in parallel and serial configurations to achieve the highest efficiency concerning the desired applications such as an add-drop filter (ADF) and a power splitter. Moreover, in the achieved optimum double and triple PCRRs, the effect of coupling radius change has been discussed. © 2024 Walter de Gruyter GmbH. All rights reserved.

关键词： Photonic crystals

来源：评论

学校读者我要写书评

暂无评论

Hyper-Parameter Tuning with Grid and Randomized Search Techniques for Predictive Models of Hotel Booking

Hyper-Parameter Tuning with Grid and Randomized Search Techn...

引用

2023 IEEE International Conference on Electrical, Electronics, Communication and computers, ELEXCOM 2023

作者： Yadav, Abhay Raj Shekhar, Sushant Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Computer Science Engineering Dehradun India Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350305111

The tourism and hospitality industries rely heavily on the hotel industry, making it crucial for hotels to optimize their business strategies. Predicting hotel bookings is one strategy that can enable hotel management to make informed decisions about pricing, marketing, and resource allocation. In this paper, we explore the use of machine learning algorithms to predict hotel bookings, focusing on two types of hotels, leisure and business hotels. We use a dataset from Kaggle containing information on hotel bookings, including 32 features such as hotel type, arrival date, departure date, and booking date. We pre-process the data by converting categorical variables into numerical variables, imputing missing values, and performing feature scaling. We evaluate various machine learning algorithms on the dataset, including Gradient Boosting Classifier, Random Forest Classifier, and Logistic Regression Classifier, using accuracy as the evaluation metric. Our results show that these three algorithms perform well on the given dataset, with the Gradient Boosting Classifier achieving the highest accuracy of 86.5%, followed by Random Forest Classifier with an accuracy of 85.2%, and Logistic Regression Classifier with an accuracy of 80.7%. Our findings demonstrate the potential of machine learning techniques in predicting hotel bookings and can be useful to hotel management in optimizing their business strategies. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Auto Insurance Fraud Detection with Multimodal Learning

引用

Data Intelligence 2023年第2期5卷 388-412页

作者： Jiaxi Yang Kui Chen Kai Ding Chongning Na Meng Wang Financial Technological Research Center Zhejiang LabHangzhou 361005China School of Computer Science and Engineering Southeast UniversityNanjing 211189China

In recent years,feature engineering-based machine learning models have made significant progress in auto insurance fraud ***,most models or systems focused only on structural data and did not utilize multi-modal data to improve fraud detection *** solve this problem,we adapt both natural language processing and computer vision techniques to our knowledge-based algorithm and construct an Auto Insurance Multi-modal Learning(AIML)*** then apply AIML to detect fraud behavior in auto insurance cases with data from real scenarios and conduct experiments to examine the improvement in model performance with multi-modal data compared to baseline model with structural data only.A selfdesigned Semi-Auto Feature Engineer(SAFE)algorithm to process auto insurance data and a visual data processing framework are embedded within *** show that AIML substantially improves the model performance in detecting fraud behavior compared to models that only use structural data.

关键词： Auto Insurance Multi-modal Learning Fraud detection Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Beyond p-y method:A review of artificial intelligence approaches for predicting lateral capacity of drilled shafts in clayey soils

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年第9期16卷 3812-3840页

作者： M.E.Al-Atroush A.E.Aboelela Ezz El-Din Hemdan Civil and Environmental Engineering Program Engineering Management DepartmentCollege of EngineeringPrince Sultan UniversityRiyadhSaudi Arabia Department of Structural Engineering Faculty of EngineeringAin Shams UniversityCairoEgypt Structure and Materials Research Lab Prince Sultan UniversityRiyadhSaudi Arabia Computer Science and Engineering Department Faculty of Electronic EngineeringMenoufia UniversityMenoufiaEgypt

In 2023,pivotal advancements in artificial intelligence(AI)have significantly *** that in mind,traditional methodologies,notably the p-y approach,have struggled to accurately model the complex,nonlinear soil-structure interactions of laterally loaded large-diameter drilled *** study undertakes a rigorous evaluation of machine learning(ML)and deep learning(DL)techniques,offering a comprehensive review of their application in addressing this geotechnical challenge.A thorough review and comparative analysis have been carried out to investigate various AI models such as artificial neural networks(ANNs),relevance vector machines(RVMs),and least squares support vector machines(LSSVMs).It was found that despite ML approaches outperforming classic methods in predicting the lateral behavior of piles,their‘black box'nature and reliance only on a data-driven approach made their results showcase statistical robustness rather than clear geotechnical insights,a fact underscored by the mathematical equations derived from these ***,the research identified a gap in the availability of drilled shaft datasets,limiting the extendibility of current findings to large-diameter *** extensive dataset,compiled from a series of lateral loading tests on free-head drilled shaft with varying properties and geometries,was introduced to bridge this *** paper concluded with a direction for future research,proposes the integration of physics-informed neural networks(PINNs),combining data-driven models with fundamental geotechnical principles to improve both the interpretability and predictive accuracy of AI applications in geotechnical engineering,marking a novel contribution to the field.

关键词： Laterally loaded drilled shaft load transfer and failure mechanisms Physics-informed neural networks(PINNs) P-y curves Artificial intelligence(AI) Dataset

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：