检索结果-内蒙古大学图书馆

Machine Memory Intelligence: Inspired by Human Memory Mechanisms

engineering 2025年

作者： Qinghua Zheng Huan Liu Xiaoqing Zhang Caixia Yan Xiangyong Cao Tieliang Gong Yong-Jin Liu Bin Shi Zhen Peng Xiaocen Fan Ying Cai Jun Liu School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Translational Research Institute of Brain and Brain-Like Intelligence Shanghai Fourth People’s Hospital Shanghai 200434 China School of Medicine Tongji University Shanghai 200092 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Department of Computer Science Iowa State University Ames IA 50011 USA

Large models, exemplified by ChatGPT, have reached the pinnacle of contemporary artificial intelligence (AI). However, they are plagued by three inherent drawbacks: excessive training data and computing power consumption, susceptibility to catastrophic forgetting, and a deficiency in logical reasoning capabilities within black-box models. To address these challenges, we draw insights from human memory mechanisms to introduce “machine memory,” which we define as a storage structure formed by encoding external information into a machine-representable and computable format. Centered on machine memory, we propose the brand-new machine memory intelligence (M 2 I) framework, which encompasses representation, learning, and reasoning modules and loops. We explore the key issues and recent advances in the four core aspects of M 2 I, including neural mechanisms, associative representation, continual learning, and collaborative reasoning within machine memory. M 2 I aims to liberate machine intelligence from the confines of data-centric neural networks and fundamentally break through the limitations of existing large models, driving a qualitative leap from weak to strong AI.

关键词： Machine memory intelligence Neural mechanism Associative representation Continual learning Collaborative reasoning

来源：评论

学校读者我要写书评

暂无评论

Implementation of deep learning in drug design

MedComm - Future Medicine

引用

MedComm - Future Medicine 2022年第2期1卷

作者： Yang, Bo Li, Kan Zhong, Xiuqin Zou, Jun Center for Clinical Translational Innovations Molecular Medicine Research Center West China Biomedical Big Data Center State Key Laboratory of Biotherapy West China Hospital West China School of Medicine Sichuan University Chengdu China Department of Pharmacy Chengdu Seventh People's Hospital The Affiliated Tumor Hospital of Chengdu Medical College Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

The field of deep learning has witnessed dramatic and rapid progress in the past several years, largely driven by the availability of massive datasets and increased computational power. Although promising advances have been made, the implementation of deep learning in drug design is still in the vigorously developing stage. Here we summarize the frontiers and emerging applications of deep learning in drug design. We provide the background of deep learning and the architecture of several important deep neural networks for drug design and discovery, including convolutional neural networks, recurrent neural networks, transformer, deep auto-encoder, generative adversarial networks, graph neural networks, and flow-based neural networks. We give some examples of tasks for which these different deep neural networks are suitable. The successful employment of deep learning in drug design and discussing its further opportunities are reviewed, such as molecular representation, drug-likeness prediction, de novo molecular generation, ligand-protein interaction prediction, reaction, and retrosynthetic prediction. Current challenges and further possibilities are proposed to help accelerate the progress of the field, such as model interpretation, the requirement for large quantities of training datasets, hyperparameters tuning, and open source. © 2022 The Authors. MedComm – Future Medicine published by John Wiley & Sons Australia, Ltd on behalf of Sichuan International Medical Exchange & Promotion Association (SCIMEA).

关键词： artificial intelligence deep learning drug design machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Log data Analysis Management System Based on Hadoop

引用

Journal of Information Hiding and Privacy Protection 2020年第2期2卷 59-65页

作者： Dunhong Yao Yu Chen School of Computer Science and Engineering Huaihua UniversityHuaihua418000China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000China School of Computer Science and Engineering Yulin Normal UniversityYulin537000China

With the rapid development of the Internet,many enterprises have launched their network *** users browse,search,and click the products of these platforms,most platforms will keep records of these network behaviors,these records are often heterogeneous,and it is called log *** effectively to analyze and manage these heterogeneous log data,so that enterprises can grasp the behavior characteristics of their platform users in time,to realize targeted recommendation of users,increase the sales volume of enterprises’products,and accelerate the development of ***,we follow the process of big data collection,storage,analysis,and visualization to design the system,then,we adopt HDFS storage technology,Yarn resource management technology,and gink load balancing technology to build a Hadoop cluster to process the log data,and adopt MapReduce processing technology and data warehouse hive technology analyze the log data to obtain the ***,the obtained results are displayed visually,and a log data analysis system is successfully *** has been proved by practice that the system effectively realizes the collection,analysis and visualization of log data,and can accurately realize the recommendation of products by *** system is stable and effective.

关键词： Log data Hadoop data analysis data visualization

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to ‟Joint optimization of infrastructure deployment and fleet operations for an electric car sharing system by considering multi-type vehicles” [J. Clean. Prod. 414 (2023) 137681]

引用

Journal of Cleaner Production 2023年 422卷

作者： Qiuyue Sai Jun Bi Xiaomei Zhao Wei Guan Chaoru Lu School of Traffic and Transportation Beijing Jiaotong University Beijing 100044 China Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University Beijing 100044 China Department of Civil Engineering and Energy Technology Oslo Metropolitan University Oslo 0166 Norway

来源：评论

学校读者我要写书评

暂无评论

Improved drug-target interaction prediction with Intermolecular Graph Transformer

arXiv

引用

arXiv 2021年

作者： Liu, Siyuan Wang, Yusong Wang, Tong Deng, Yifan He, Liang Shao, Bin Yin, Jian Zheng, Nanning Liu, Tie-Yan School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Microsoft Research Asia Beijing100080 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an710049 China School of Computer Science Fudan University Shanghai200433 China

The identification of active binding drugs for target proteins (termed as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential role in drug discovery. Although recent deep learning-based approaches achieved better performance than molecular docking, existing models often neglect certain aspects of the intermolecular information, hindering the performance of prediction. We recognize this problem and propose a novel approach named Intermolecular Graph Transformer (IGT) that employs a dedicated attention mechanism to model intermolecular information with a three-way Transformer-based architecture. IGT outperforms state-of-the-art approaches by 9.1% and 20.5% over the second best for binding activity and binding pose prediction respectively, and shows superior generalization ability to unseen receptor proteins. Furthermore, IGT exhibits promising drug screening ability against SARS-CoV-2 by identifying 83.1% active drugs that have been validated by wet-lab experiments with near-native predicted binding poses. © 2021, CC BY-NC-SA.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithm for Judicial Judgment Prediction Based on BERT

Deep Learning Algorithm for Judicial Judgment Prediction Bas...

引用

IEEE International Conference on Computing, Communication and Security (ICCCS)

作者： Yongjun Wang Jing Gao Junjie Chen Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture And Animal Husbandry College of Computer Science and Information Engineering Inner Mongolia Agricultural University Inner Mongolia Hohhot China

ISBN: (数字)9781728191805

ISBN: (纸本)9781728191812

With the continuous development of artificial intelligence AI, machine learning and deep learning algorithms have been applied to more fields and scenarios, changing people's work and lifestyle, which also brought new development and opportunities to the judicial field. Judicial case judgment is a very important work in the legal field, and it is an indispensable process for judges to determine the nature and punishment of criminals. Judgment prediction can be seen as a multi-label text classification problem. Based on a large number of text files of judicial cases, we use the recently very popular pre-training language model Bidirectional Encoder Representations from Transformers (BERT) to train word embedding of the case data, and combines deep learning model algorithms such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Deep Pyramid CNN (DPCNN), Recurrent Convolutional Neural Networks (RCNN) to predict judgment in judicial cases. Experimental results demonstrate that compared with the 6 methods of baseline, the deep learning model based on the BERT word embedding achieves significant improvements that accuracy of prediction can be increased by 8%-10%, which can help judges and lawyers make more accurate judgments.

关键词： Law Bit error rate Task analysis data models Predictive models Training Deep learning

来源：评论

学校读者我要写书评

暂无评论

HPV-CCDC106 integration alters local chromosome architecture and hijacks an enhancer by three-dimensional genome structure remodeling in cervical cancer

引用

Journal of Genetics and Genomics 2020年第8期47卷 435-448页

作者： Canhui Cao Ping Hong Xingyu Huang Da Lin Gang Cao Liming Wang Bei Feng Ping Wu Hui Shen Qian Xu Ci Ren Yifan Meng Wenhua Zhi Ruidi Yu Juncheng Wei Wencheng Ding Xun Tian Qinghua Zhang Wei Li Qinglei Gao Gang Chen Kezhen Li Wing-Kin Sung Zheng Hu Hui Wang Guoliang Li Peng Wu Department of Gynecologic Oncology Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan430030China Cancer Biology Research Center(Key Laboratory of the Ministry of Education) Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan430030China National Key Laboratory of Crop Genetic Improvement Huazhong Agricultural UniversityWuhan430070China Agricultural Bioinformatics Key Laboratory of Hubei Province Hubei Engineering Technology Research Center of Agricultural Big DataCollege of InformaticsHuazhong Agricultural UniversityWuhan430070China State Key Laboratory of Agricultural Microbiology Huazhong Agricultural UniversityWuhan430070China Bio-Medical Center Huazhong Agricultural UniversityWuhan430070China College of Veterinary Medicine Huazhong Agricultural UniversityWuhan430070China Department of Obstetrics and Gynecology Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan430022China Department of Obstetrics and Gynecology Key Laboratory for Molecular Diagnosis of Hubei ProvinceThe Central Hospital of WuhanTongji Medical CollegeHuazhong University of Science and TechnologyWuhan430010China Department of Computational and Systems Biology Genome Institute of SingaporeSingapore Department of Gynecological Oncology The First Affiliated Hospital of Sun Yat-sen UniversityGuangzhou510080China

Integration of human papillomavirus(HPV)DNA into the human genome is a reputed key driver of cervical ***,the effects of HPV integration on chromatin structural organization and gene expression are largely *** studied a cohort of 61 samples and identified an integration hot spot in the CCDC106 gene on chromosome *** then selected fresh cancer tissue that contained the unique integration loci at CCDC106 with no HPV episomal DNA and performed whole-genome,RNA,chromatin immunoprecipitation and high-throughput chromosome conformation capture(Hi-C)sequencing to identify the mechanisms of HPV integration in cervical *** analyses indicated that chromosome 19 exhibited significant genomic variation and differential expression densities,with correlation found between three-dimensional(3D)structural change and gene ***,HPV integration divided one topologically associated domain(TAD)into two smaller TADs and hijacked an enhancer from PEG3 to CCDC106,with a decrease in PEG3 expression and an increase in CCDC106 *** expression dysregulation was further confirmed using 10 samples from our cohort,which exhibited the same HPV-CCDC106 *** summary,we found that HPV-CCDC106 integration altered local chromosome architecture and hijacked an enhancer via 3D genome structure ***,this study provides insight into the 3D structural mechanism underlying HPV integration in cervical carcinogenesis.

关键词： Cervical cancer HPV integration Fusion gene Hi-C Enhancer TAD

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving and Verifiable Federated Learning Scheme

A Privacy-Preserving and Verifiable Federated Learning Schem...

引用

IEEE International Conference on Communications (ICC)

作者： Xianglong Zhang Anmin Fu Huaqun Wang Chunyi Zhou Zhenzhu Chen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing PR China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing PR China

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

Due to the complexity of the data environment, many organizations prefer to train deep learning models together by sharing training sets. However, this process is always accompanied by the restriction of distributed storage and privacy. Federated learning addresses this challenge by only sharing gradients with the server without revealing training sets. Unfortunately, existing research has shown that the server could extract information of the training sets from shared gradients. Besides, the server may falsify the calculated result to affect the accuracy of the trained model. To solve the above problems, we propose a privacy-preserving and verifiable federated learning scheme. Our scheme focuses on processing shared gradients by combining the Chinese Remainder Theorem and the Paillier homomorphic encryption, which can realize privacy-preserving federated learning with low computation and communication costs. In addition, we introduce the bilinear aggregate signature technology into federated learning, which effectively verifies the correctness of aggregated gradient. Moreover, the experiment shows that even with the added verification function, our scheme still has high accuracy and efficiency.

关键词： Servers Machine learning Training Encryption Aggregates Computational modeling Privacy

来源：评论

学校读者我要写书评

暂无评论

Correction to: Magnetic Particle Imaging-Guided Hyperthermia for Precise Treatment of Cancer: Review, Challenges, and Prospects

引用

Molecular imaging and biology 2023年第6期25卷 1151页

作者： Siao Lei Jie He Pengli Gao Yueqi Wang Hui Hui Yu An Jie Tian School of Engineering Medicine & School of Biological Science and Medical Engineering Beihang University Beijing 100191 China. Key Laboratory of Big Data-Based Precision Medicine (Beihang University) Ministry of Industry and Information Technology of the People's Republic of China Beijing 100191 People's Republic of China. CAS Key Laboratory of Molecular Imaging Institute of Automation Beijing 100190 China. School of Engineering Medicine & School of Biological Science and Medical Engineering Beihang University Beijing 100191 China. yuan1989@***. Key Laboratory of Big Data-Based Precision Medicine (Beihang University) Ministry of Industry and Information Technology of the People's Republic of China Beijing 100191 People's Republic of China. yuan1989@***. CAS Key Laboratory of Molecular Imaging Institute of Automation Beijing 100190 China. yuan1989@***. School of Engineering Medicine & School of Biological Science and Medical Engineering Beihang University Beijing 100191 China. tian@***. Key Laboratory of Big Data-Based Precision Medicine (Beihang University) Ministry of Industry and Information Technology of the People's Republic of China Beijing 100191 People's Republic of China. tian@***. CAS Key Laboratory of Molecular Imaging Institute of Automation Beijing 100190 China. tian@***. Zhuhai Precision Medical Center Zhuhai People's Hospital Affiliated With Jinan University Zhuhai 519000 China. tian@***.

来源：评论

学校读者我要写书评

暂无评论

Cover Feature: The Configuration Identification of Guanine Molecules Adsorbed on the Si(100) Surface by Using XPS Shake-up Satellites and NEXAFS (ChemPhysChem 20/2024)

引用

ChemPhysChem 2024年第20期25卷

作者： Shuyi Wang Jingdong Guo Hujun Shen Xiong Li Chao Cen Shaohong Cai Mingsen Deng College of Big Data and Information Engineering Guizhou University Guiyang 550025 China Guizhou Provincial Key Laboratory of Computational Nano-material Science Guizhou Education University Guiyang 550018 China School of Information Guizhou University of Finance and Economics Guiyang 550025 China Moutai Institute Renhuai 564507 China National Engineering Research Center for Compounding and Modification of Polymer Materials Guiyang 550014 China

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：