检索结果-内蒙古大学图书馆

Sparse Learning for Neural Networks with A Generalized Sparse Regularization

Procedia Computer Science 2022年 214卷 747-754页

作者： Anda Tang Tongsheng Yao Lingfeng Niu Yong Shi School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China

Deep neural networks (DNNs) is very important and have achieved remarkable accuracies in tasks such as image processing. However, the success of DNNs heavily relies on excessive computation and parameter storage costs. To cut down the overheads, a wide range of regularization terms are proposed on netwok compression, which have their own scope of application though. To further reduce computation, structural sparsity learning is a matter of great concern where group sparse regularizations are blossoming in radiant splendour. However, the group sparse regularizations used in network compression is relatively scarce. A majority of structural compression only stem from ℓ 2,1 regularization. In addition, sparse regularization in structural network compression lacks unified form and theoretical guidance. Therefore, we focus our attention on a generalized sparse regularization in sparse learning of deep learning. We put a series of sparse regularization into a framework where some group sparse regularizations with different properties are introduced. The transformation of regularizations can be completed through the selection of hyper-parameters. In this case, we can use the optimization strategy for unification and theoretical guidance, and transform different sparse regularizations to adapt to different tasks. To our knowledge, it is the first work applying the generalized sparse regularization with novel group sparsity in compression of DNNs. The proposed ℓ p , q , r regularization can achieve both neuron-level and connection-level sparsity. And we give the analytical solutions for some specific ( p,q, r ) thus the compression can be achieved throughout the standard optimization process. We perform extensive experiments to illustrate the advantages and characteristics of our new method for further applications.

关键词： Deep neural networks Model compression Group Sparse optimization Regularization Sparse Learning

来源：评论

学校读者我要写书评

暂无评论

Exploring data science in IT and quantitative management: Preface for ITQM 2015

引用

Procedia Computer Science 2015年 55卷 1-7页

作者： Gomes, Luiz Flavio Autran Monteiro Shi, Yong Colcher, Raul Wolcott, Peter Herrera-Viedma, Enrique Ibmec/RJ Av. Presidente Wilson 118 11th floor Rio de Janeiro RJ Brazil Research Center on Fictitiotus Economy and Data Science Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China College of Information Science and Technology University of Nebraska at Omaha OmahaNE United States ASSESPRO Brazil DECSAI C/ Periodista Daniel Saucedo Aranda University of Granada Granada Spain

来源：评论

学校读者我要写书评

暂无评论

A Brief Survey of Distribution Robust Graph Neural Networks 11

A Brief Survey of Distribution Robust Graph Neural Networks

引用

11th International Conference on Information Technology and Quantitative management, ITQM 2024

作者： Zheng, Lei Quan, Pei Shi, Yong Niu, Lingfeng The School of Mathematical Sciences University of Chinese Academy of Sciences Beijing100190 China The College of Economics and Management Beijing University of Technology Beijing100124 China The School of Economics and Management University of Chinese Academy of Sciences Beijing1001090 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

Graph neural network is a powerful tool for solving various graph tasks, such as node classification and graph classification. However, there is increasing evidence suggesting that it is sensitive to distribution shifts and its performance is reduced by at least 10% when distribution shifts happen. In the last three years, to solve the wide existing distribution shifts, some distribution robust strategies have been designed specifically for graph neural networks. It is also one of the popular research topics in graph neural networks in recent years. Therefore, in this paper, we divide these strategies into three categories depending on the specific problems they solve: distribution shift for semi-supervised node classification, distribution shift for unsupervised node classification, and out-of-distribution shift for graph classification. Furthermore, we discuss and summarize the strategies for each type of problem. After investigating these strategies, we put forward future development direction. © 2024 The Authors.

关键词： Distribution generalization Graph neural networks Shift robust

来源：评论

学校读者我要写书评

暂无评论

Impact of the China Railway Express on Employment Structure - Evidence from Urban Economic data 11

Impact of the China Railway Express on Employment Structure ...

引用

11th International Conference on Information Technology and Quantitative management, ITQM 2024

作者： Yan, Bochao Jiang, Hailiang Wu, Junfeng Tian, Xin China Agricultural University Beijing100083 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China Shanghai WinJoin Information Technology Co. Ltd. Shanghai200126 China

As the main international trade channel of China's "westward development", the opening of China Railway Express has significantly improved the trade facilitation of countries along the route. This paper investigates the impact of the opening of China Railway Express sites on the employment choices of individuals by using the difference in difference method based on the economic panel data of China's prefecture-level cities and the data on the opening of China Railway Express during the period of 2007~2019, which are matched by the correlation. The results of the study show that the opening of the China Railway Express increases the probability of individuals within the radiation area to enter the private sector for employment. The empirical results provide a new explanatory mechanism for the opening of the China Railway Express on economic growth, which has certain theoretical and policy value. © 2024 The Authors.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Real Estate with AI: An agent based on LangChain 11

Real Estate with AI: An agent based on LangChain

引用

11th International Conference on Information Technology and Quantitative management, ITQM 2024

作者： Haurum, Kasper Raupach Ma, Ruiqi Long, Wen Business School Aalborg University Aalborg9220 Denmark Sino-Danish College University of Chinese Academy of Sciences Beijing100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining & Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China

Recent developments in large language models (LLMs) have opened new avenues for the real estate industry. These models not only understand language but also function as intelligent agents, engaging with investors through open-ended conversations and influencing their decision-making. Utilizing unstructured data from a professional Danish real estate website, we developed a real estate AI agent in both English and Danish using LangChain and Pinecone. Through testing and evaluation, our agent has demonstrated superior professional and concise outputs compared to other LLMs like Doubao and ChatGPT 4 and shown excellent performance and effectiveness. Our work serves as a reference for AI in real estate investment-related research and proposes new solutions to the "unprofessional foundation " and " expensive consulting fee" problems encountered by ordinary investors in their investment decisions. © 2024 The Authors.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Forecasting Chinese Stock Market Prices using Baidu Search Index with a Learning-Based data Collection Method

Forecasting Chinese Stock Market Prices using Baidu Search I...

引用

作者： Dong, Jichang Dai, Wei Liu, Ying Yu, Lean Wang, Jie School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Economics and Management Beijing University of Chemical Technology Beijing100029 China Department of Civil and Environmental Engineering Stanford University StanfordCA94305 United States

In this study, to address search index selection and volatility problems, we propose a learning-based search index collection method that collects the search data fraction for modeling by learning the best criteria from robust statistics. Based on the fraction of collected search index from internet search engine (***) data sources, a novel model is formulated for Chinese stock market price forecasting. We empirically test our method on the two main Chinese stock market price indexes and discover that the prediction accuracy is equivalent or superior to the benchmarks from previous studies that used alternative search index collection methods or lagged data prediction models. All prediction results outstand the importance of an effective data collection method for the robustness of forecast models and demonstrate the utility of a learning-based collection method for addressing search index collection problem, leading to a significant improvement in Chinese stock market price prediction accuracy. © 2019 World Scientific Publishing Company.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Global Green Digital Economy: Challenges and Development: Preface for ITQM 2022

引用

Procedia Computer Science 2022年第C期214卷 1-3页

作者： Shi, Yong Li, Jianping Kou, Gang Berg, Daniel Tien, James College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States Research Centre on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China School of Business Administration Southwestern University of Finance and Economics Chengdu611130 China College of Engineering University of Miami Coral GablesFL33124 United States

来源：评论

学校读者我要写书评

暂无评论

Three IQs of AI systems and their testing methods

Three IQs of AI systems and their testing methods

引用

3rd Asian Conference on Artificial Intelligence Technology, ACAIT 2019

作者： Liu, Feng Liu, Ying Shi, Yong Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States

The rapid development of artificial intelligence (AI) has brought the AI threat theory as well as the problem about how to evaluate the intelligence level of intelligent products. Both need to find a quantitative method to evaluate the intelligence level of intelligence systems, including human intelligence. Based on the standard intelligence system and the extended Von Neumann architecture, this study proposes General intelligence quotient (IQ), Service IQ and Value IQ evaluation methods for intelligence systems, depending on different evaluation purposes. Among them, the General IQ of intelligence systems is to answer the question of whether 'the artificial intelligence can surpass the human intelligence', which is reflected in putting the intelligence systems on an equal status and conducting the unified evaluation. The Service IQ and Value IQ of intelligence systems are used to answer the question of 'how the intelligent products can better serve the human', reflecting the intelligence and required cost of each intelligence system as a product in the process of serving human. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Testing

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Clustering Algorithms

引用

Annals of data Science 2015年第2期2卷 165-193页

作者： Dongkuan Xu Yingjie Tian School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

data analysis is used as a common method in modern science research, which is across communication science, computer science and biology science. Clustering, as the basic composition of data analysis, plays a significant role. On one hand, many tools for cluster analysis have been created, along with the information increase and subject intersection. On the other hand, each clustering algorithm has its own strengths and weaknesses, due to the complexity of information. In this review paper, we begin at the definition of clustering, take the basic elements involved in the clustering process, such as the distance or similarity measurement and evaluation indicators, into consideration, and analyze the clustering algorithms from two perspectives, the traditional ones and the modern ones. All the discussed clustering algorithms will be compared in detail and comprehensively shown in Appendix Table 22.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impact of IT Capability on Inventory management: An Empirical Study

引用

Procedia Computer Science 2022年 199卷 142-148页

作者： Xin Tian Haoqing Wang Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China

Despite the widespread adoption of technology in inventory management, empirical research that examines the effect of these technologies is scarce. Does IT capability really have a positive effect on the inventory management? This paper empirically studies the usage of information technology by the definition of IT capability. Our unique panel data set allows us to explore the relationship between technology usage and inventory management. Our results show that IT capability has a positive effect on the inventory strategy and inventory operation process, and has a negative effect on the out-of-stock level. Our research demonstrates the superiority of the usage of technology.

关键词： intelligent warehousing business intelligence inventory management logistics

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：