检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Mrinmay Sen A. K. Qin Gayathri C Raghu Kishore N Yen-Wei Chen Balasubramanian Raman Dept. of Computing Technologies Swinburne University of Technology Hawthorn Victoria Australia Dept. of Artificial Intelligence Indian Institute of Technology Hyderabad Hyderabad India Dept. of Computer Science and Engineering Mahindra University Hyderabad India Dept. of Information Science and Engineering Ritsumeikan University Kyoto Japan Dept. of Computer Science and Engineering Indian Institute of Technology Roorkee Roorkee India

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton’s gradient update in large-scale stochastic optimization of machine learning models. It can be viewed as a variant of natural gradient descent, where the challenge of storing and calculating the full FIM is addressed through making use of the regularized FIM and directly finding the gradient update direction via Sherman-Morrison matrix inversion. Additionally, like the popular Adam method, SOFIM uses the first moment of the gradient to address the issue of non-stationary objectives across mini-batches due to heterogeneous data. The utilization of the regularized FIM and Sherman-Morrison matrix inversion leads to the improved convergence rate with the same space and time complexities as stochastic gradient descent (SGD) with momentum. The extensive experiments on training deep learning models using several benchmark image classification datasets demonstrate that the proposed SOFIM outperforms SGD with momentum and several state-of-the-art Newton optimization methods in term of the convergence speed for achieving the pre-specified objectives of training and test losses as well as test accuracy.

关键词： Training Deep learning Accuracy Neural networks Stochastic processes Optimization methods Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

SOFIM: Stochastic Optimization Using Regularized Fisher information Matrix

arXiv

引用

arXiv 2024年

作者： Sen, Mrinmay Qin, A.K. Gayathri, C. Kishore, Raghu N. Chen, Yen-Wei Raman, Balasubramanian Dept. of Computing Technologies Swinburne University of Technology HawthornVIC Australia Dept. of Artificial Intelligence Indian Institute of Technology Hyderabad Hyderabad India Dept. of Computer Science and Engineering Mahindra University Hyderabad India Dept. of Information Science and Engineering Ritsumeikan University Kyoto Japan Dept. of Computer Science and Engineering Indian Institute of Technology Roorkee Roorkee India

This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton's gradient update in large-scale stochastic optimization of machine learning models. It can be viewed as a variant of natural gradient descent, where the challenge of storing and calculating the full FIM is addressed through making use of the regularized FIM and directly finding the gradient update direction via Sherman-Morrison matrix inversion. Additionally, like the popular Adam method, SOFIM uses the first moment of the gradient to address the issue of non-stationary objectives across mini-batches due to heterogeneous data. The utilization of the regularized FIM and Sherman-Morrison matrix inversion leads to the improved convergence rate with the same space and time complexities as stochastic gradient descent (SGD) with momentum. The extensive experiments on training deep learning models using several benchmark image classification datasets demonstrate that the proposed SOFIM outperforms SGD with momentum and several state-of-the-art Newton optimization methods in term of the convergence speed for achieving the pre-specified objectives of training and test losses as well as test accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Fisher information matrix

来源：评论

学校读者我要写书评

暂无评论

Inflation Prediction: A Comparative Study of ARIMA and LSTM Models Across Different Temporal Resolutions

Inflation Prediction: A Comparative Study of ARIMA and LSTM ...

引用

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： T Lakshmi Narayanaa R R Skandarsini S. Jhansi Ida S. Rathana Sabapathy P Nanthitha Dept. of Computer Science and Business Systems RMK Engineering College Thiruvallur India Dept. of Information Technology Panimalar Engineering College Chennai India

This research study focuses on the prediction of inflation rates using two distinct models, Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM), tailored to accommodate the temporal resolutions of monthly and quarterly inflation data. While a comprehensive evaluation across varying time horizons was not conducted, the results suggest that the ARIMA model excels in short-term forecasting, as evidenced by its impressive performance on a 2021 holdout dataset. Conversely, the LSTM model displays potential for medium-term predictions. This study underscores the significance of aligning forecasting models with data characteristics, emphasizes the importance of temporal resolution, and discusses potential avenues for improvement, such as multivariate modeling or alternative techniques like Prophet. The findings have broad implications for economists, policymakers, and analysts seeking precise inflation forecasts, shedding light on the nuanced interplay between models and data in the domain of inflation prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Interest Representation Network for Click-Through Rate Prediction

Evolutionary Interest Representation Network for Click-Throu...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Zhou, Renjie Jin, Zhenming Wan, Jian Zhang, Jilin Guo, Xingyu Liu, Qiang Hangzhou Dianzi University Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education School of Computer Science and Technology Hangzhou China Hangzhou Dianzi University Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education Itmo Joint Institute Hangzhou China Zhejiang University of Science and Technology School of Information and Electronic Engineering Hangzhou China Zhejiang Police College Dept. of Computer and Information Technology Hangzhou China

ISBN: (纸本)9798350304855

The rapid development of the Internet has revo-lutionized our lives, providing us with an array of convenient services. However, this revolution has also led to the problem of data overload. Personalized recommendation services have been widely recognized as an effective solution to this problem by both the industrial and academic communities. Accurate prediction of click-through rate (CTR) is a critical task in personalized recommendation systems.since it can improve the user's shopping experience, ultimately increasing revenue for the platform. To achieve accurate CTR prediction, it is crucial to capture user interests. While several methods for interest modeling exist, challenges related to user interest evolution and user behavior noise need further attention. This paper proposes a novel CTR prediction model named the Evolutionary Interest Representation Network (EIRN), which learns the evolving interest representation of users from their behaviors, profiles, and environmental attributes. In the model, we introduce an advertisement correlation graph decomposition layer and a noise filter layer to enhance and purify the user behavior representation. An interest extraction layer is designed to capture sequential correlations and common characteristics between user behaviors, representing their interests. Additionally, as user interests evolve over time and their importance changes, an attention-based interest evolution layer is designed to track the evolution of user interests. Our proposed method is validated using four public datasets and an industrial dataset, showing its superiority over existing CTR prediction methods. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Analysis of the PV Energy Potential in the Bulgarian Danube River Region between Ruse and Silistra

Analysis of the PV Energy Potential in the Bulgarian Danube ...

引用

Communications, information, Electronic and Energy systems.(CIEES), International Conference on

作者： Katerina Gabrovska-Evstatieva Ivaylo Stoyanov Tsvetelina Kaneva Nikolay Valov Vladimir Tsankov Boris Evstatiev Nicolay Mihailov Dept. of Computer Science University of Ruse Ruse Bulgaria Dept. of Electric Power Engineering University of Ruse Ruse Bulgaria Dept. of Computer Systems and Technologies University of Ruse Ruse Bulgaria Dept. of Automation and Electronics University of Ruse Ruse Bulgaria

ISBN: (数字)9798350352863

ISBN: (纸本)9798350352870

The goal of the study is to assess and compare the photovoltaic energy potential in the central-eastern part of the Bulgarian Danube region between the cities of Ruse and Silistra. To achieve this the solar radiation and the temperature of the environment should be obtained and analyzed. The goal of the study is to assess and compare the photovoltaic energy potential in the central-eastern part of the Bulgarian Danube region between the cities of Ruse and Silistra. To achieve this the solar radiation and the temperature of the environment should be obtained and analyzed. The goal of the study is to assess and compare the photovoltaic energy potential in the central-eastern part of the Bulgarian Danube region between the cities of Ruse and Silistra. To achieve this the solar radiation and the temperature of the environment should be obtained and analyzed.

关键词： Photovoltaic systems Electric potential Temperature distribution Renewable energy sources Urban areas Rivers Solar radiation Thermal pollution

来源：评论

学校读者我要写书评

暂无评论

Design of efficient single-etch grating couplers for silicon nitride photonics at 1550 nm

Design of efficient single-etch grating couplers for silicon...

引用

2024 Photonics North, PN 2024

作者： Fraser, William Benedikovic, Daniel Korcek, Radovan Milanizadeh, Maziyar Bucio, Thalía Domínguez Vitali, Valerio Gardes, Frederic Y. Schmid, Jens H. Cheben, Pavel Ye, Winnie N. Dept. Electronics Carleton University Ottawa Canada Dept. Multimedia and Information-Communication Technologies University of Zilina Zilina Slovakia University Science Park University of Zilina Zilina Slovakia National Research Council Ottawa Canada Optoelectronics Research Centre University of Southampton Highfield Campus Southampton United Kingdom Electrical Computer and Biomedical Engineering Department University of Pavia Pavia27100 Italy

ISBN: (纸本)9798350366365

We present the design of single-etch grating couplers implemented on native and a hybrid silicon nitride (SiN) photonic platform with amorphous silicon (α-Si) overlays, operating in the telecom waveband. The SiN-only grating coupler has a coupling loss of -3.6 dB and a 1-dB bandwidth of 37 nm. A hybrid α-Si-on-SiN platform yields improved coupling loss of -1.4 dB and -1 dB for uniform and subwavelength grating apodized designs, respectively. © 2024 IEEE.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Improving E-commerce Fraud Detection via Machine Learning: Comparative Evaluation of Model Effectiveness

Improving E-commerce Fraud Detection via Machine Learning: C...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical systems. ICSES 2023

作者： Gangalakshmi, T. Sathya, V. Vinodhini, S. Chandralekha, E. Usha, V. Ravikumar, S. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Dept.of CSE Chennai India Veltech Multitech Dr.Rangarajan Dr.Sakunthala Engineering College Dept.of Computer Science and Business Systems Chennai India Velammal Engineering College Dept. of Information Technology Chennai India

ISBN: (纸本)9798350319200

In the fast-growing E-commerce world, fraud has become a major concern, causing economic losses and eroding consumer trust. This work aimed to detect E-commerce fraud using machine learning on a customer dataset. The dataset contained transactional and customer data, requiring preprocessing to handle missing values and categorical features. Four models - Logistic Regression, Random Forest, Gradient Boosting, and Support Vector Classifier - were trained and evaluated for fraud detection accuracy using metrics like Accuracy, Precision, Recall, and F1-Score. Results revealed distinct model strengths and weaknesses. Logistic Regression achieved balanced performance, while Random Forest and Gradient Boosting excelled in certain aspects. Support Vector Classifier also demonstrated competitive results. This work highlights the potential of machine learning in E-commerce fraud prevention, enhancing transaction security and trust. Further research could refine and advance fraud detection techniques for online platforms. © 2023 IEEE.

关键词： E-commerce fraud Fraud detection Hybrid approach Machine learning

来源：评论

学校读者我要写书评

暂无评论

Agricultural Data Space: the METRIQA Platform and a Case Study in the CODECS project

Agricultural Data Space: the METRIQA Platform and a Case Stu...

引用

Federated Conference on computer science and information systems.(FedCSIS)

作者： Manlio Bacco Giovanna Maria Dimitri Alexander Kocian Paolo Barsocchi Antonino Crivello Gianluca Brunori Marco Gori Stefano Chessa Inst. of Information Science and Technologies (ISTI) National Research Council (CNR) Pisa Italy Dept. of Information Engineering and Mathematics (DIISM) University of Siena Italy Dept. Computer Science University of Pisa Italy Dept. of Agriculture Food and Environment University of Pisa Italy Dept. Computer Science University of Pisa Italy ISTI-CNR Italy

ISBN: (数字)9788396960160

ISBN: (纸本)9798350359718

This work describes the ongoing design and development of the METRIQA platform, hosting the Italian agrifood data space. Both are key components that the Italian National Research Centre for Agricultural technologies is putting forward in its activities. We present a high-level description of the platform, which is designed to provide web-like access to digital resources and services following an approach called Web of Agri-Food, to support the digital transformation of the sector in Italy. To show its potential, we also present a real case study demonstrating both the benefits and impacts of the proposed architecture, connecting stakeholders and authorities at different levels.

关键词： Industries Connectors computer science Data analysis Digital transformation Supply chains Companies Stakeholders Convergence information systems

来源：评论

学校读者我要写书评

暂无评论

Low power implementation of Geometric High-order Decorrelation-based Source Separation on an FPGA board

Low power implementation of Geometric High-order Decorrelati...

引用

IEEE Cool Chips

作者： Ziquan Qin Kaijie Wei Hideharu Amano Kazuhiro Nakadai Dept. of Information and Computer Science Keio University Yokohama Japan Dept. of Systems and Control Engineering Tokyo Institute of Technology Tokyo Japan

Open source software for robot audition called HARK aims to make “OpenCV” in audio signal processing, providing comprehensive functions from multichannel audio input to sound localization, sound source separation, and au-tomatic speech recognition. Since each of these HARK modules takes considerable energy when executed on PC, we propose to implement each module on an FPGA board called M-KUBOS connected. Here, we focus on the most computationally expensive function of HARK; the sound source separation, and implement it on a Zynq Ultrascale+ board. More than twice a performance improvement was achieved by using the sound frequency level parallelization in the HLS description compared to the software execution on the Ryzen 3990X64-core server. Power evaluation of the real board showed that the energy consumption is only 1/23.4 of the server.

关键词： Location awareness Energy consumption Source separation Power demand Speech recognition Parallel processing Servers

来源：评论

学校读者我要写书评

暂无评论

Quality of Experience Aware Task Offloading in Digital Twinning Vehicular Edge Computing

Quality of Experience Aware Task Offloading in Digital Twinn...

引用

International Conference on Distributed Computing in Sensor systems.(DCOSS)

作者： Mostakim Jihad Mashraba Tasnim Rodshi Abdullah Al Fahad Palash Roy Md. Abdur Razzaque Mohammad Mehedi Hassan Department of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering Green Networking Research Group University of Dhaka Bangladesh Information Systems Dept. College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia

ISBN: (数字)9798350369441

ISBN: (纸本)9798350369458

Adopting Digital Twin (DT) technology in vehicular edge computing (VEC) enables efficient capture of real-time state information of applications, thereby addressing complex task scheduling problems. Existing literature studies considered only minimizing service latency for task offloading; however, there is room for exploring strategies to enhance user Quality of Experience (QoE) in timeliness and reliability domains. In this paper, we have developed an optimization framework using Mixed Integer Linear Programming (MILP), namely QuETOD, which minimizes service latency by allocating task execution responsibility to highly reliable and reputed vehicles in a DT-enabled VEC environment. The developed QuETOD framework clusters the vehicles based on the demand-supply theory of economics by considering computing resources and utilizing the multi-weighted subjective logic for getting the proper reputation update of the vehicles. The experimental results of the developed QuETOD system depict significant performance improvement in terms of QoE and reliability compared to the state-of-the-art works as high as 15% and 25%, respectively.

关键词： Processor scheduling Computational modeling Reliability theory Real-time systems Polynomials Quality of experience Servers

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：