检索结果-内蒙古大学图书馆

Brain-inspired artificial intelligence research: A review

science China(Technological sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

来源：评论

学校读者我要写书评

暂无评论

Treeffuser: Probabilistic Predictions via Conditional Diffusions with Gradient-Boosted Trees 38

Treeffuser: Probabilistic Predictions via Conditional Diffus...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Beltran-Velez, Nicolas Grande, Alessandro Antonio Nazaret, Achille Kucukelbir, Alp Blei, David Department of Computer Science Columbia University New York United States Halvorsen Center for Computational Oncology Memorial Sloan Kettering Cancer Center New York United States Irving Institute for Cancer Dynamics Columbia University New York United States Fero Labs New York United States Department of Statistics Columbia University New York United States

Probabilistic prediction aims to compute predictive distributions rather than single point predictions. These distributions enable practitioners to quantify uncertainty, compute risk, and detect outliers. However, most probabilistic methods assume parametric responses, such as Gaussian or Poisson distributions. When these assumptions fail, such models lead to bad predictions and poorly calibrated uncertainty. In this paper, we propose Treeffuser, an easy-to-use method for probabilistic prediction on tabular data. The idea is to learn a conditional diffusion model where the score function is estimated using gradient-boosted trees. The conditional diffusion model makes Treeffuser flexible and non-parametric, while the gradient-boosted trees make it robust and easy to train on CPUs. Treeffuser learns well-calibrated predictive distributions and can handle a wide range of regression tasks-including those with multivariate, multimodal, and skewed responses. We study Treeffuser on synthetic and real data and show that it outperforms existing methods, providing better calibrated probabilistic predictions. We further demonstrate its versatility with an application to inventory allocation under uncertainty using sales data from Walmart. We implement Treeffuser in https://***/blei-lab/treeffuser. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pelvic bone region segmentation (PBRS) from X-ray image using convolutional neural network (CNN) 26

Pelvic bone region segmentation (PBRS) from X-ray image usin...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Ul Alam, Syed Alif Binte Alam, Saadia Saha, Sourav Haque, Mahmudul Rahman, Rashedur Kobashi, Syoji Independent University Bangladesh Department of Computer Science and Engineering Dhaka1229 Bangladesh Independent University Bangladesh Center for Computational & Data Sciences Dhaka1229 Bangladesh University of Hyogo Graduate School of Engineering Shosha Hyogo Himeji2167 Japan

ISBN: (纸本)9798350359015

Pelvic and hip fractures offer considerable public health risks with high morbidity and mortality rates. Because of the complicated bone structure of the pelvic bone region, detecting fractures is difficult. Though X-ray imaging is routinely utilised for detecting fractures, manual fracture diagnosis is prone to inaccuracies. This paper proposes the use of deep learning algorithms for automated segmentation of the pelvic bone region in X-ray images. In our work, we have investigated U-Net based pelvic area segmentation models with various convolutional neural network (CNN) backbones. The DenseNet121-based U-Net design emerged as the most optimal model, establishing a compromise between performance and computational efficiency. Although it had a modest loss in IoU and F1 scores when compared to InceptionNetV3, it had a remarkable 59.44% reduction in the number of parameters. © 2023 IEEE.

关键词： deep learning pelvic bone segmentation x-ray

来源：评论

学校读者我要写书评

暂无评论

Decomposition of Differences of Independent and Identically Distributed Random Variables

引用

Moscow University computational Mathematics and Cybernetics 2025年第1期49卷 67-72页

作者： Ushakov, V. G. Ushakov, N. G. Department of Computational Mathematics and Cybernetics Moscow State University Moscow Russia Institute of Informatics Problems Federal Research Center ‘‘Computer Science and Control’’ Russian Academy of Sciences Moscow Russia Norwegian University of Science and Technology Trondheim Norway

The authors consider conditions where the distribution of the components of the difference between two independent identically distributed random variables can be uniquely reconstructed with an accuracy of up to a shift and reflection. This uniqueness is essential for solving a number of characterization problems in mathematical statistics. An algorithm for estimating the components is presented for when data are given in a symmetrized form.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultrastable supported oxygen evolution electrocatalyst formed by ripening-induced embedding

引用

science (New York, N.Y.) 2025年第6735期387卷 791-796页

作者： Shi, Wenjuan Shen, Tonghao Xing, Chengkun Sun, Kai Yan, Qisheng Niu, Wenzhe Yang, Xiao Li, Jingjing Wei, Chenyang Wang, Ruijie Fu, Shuqing Yang, Yong Xue, Liangyao Chen, Junfeng Cui, Shiwen Hu, Xiaoyue Xie, Ke Xu, Xin Duan, Sai Xu, Yifei Zhang, Bo State Key Laboratory of Molecular Engineering of Polymers Department of Macromolecular Science Fudan University Shanghai China Collaborative Innovation Center of Chemistry for Energy Materials Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials MOE Key Laboratory of Computational Physical Sciences Department of Chemistry Fudan University Shanghai China Department of Chemistry and Department of Electrical and Computer Engineering Northwestern University Evanston IL United States Hefei National Laboratory Hefei China

The future deployment of terawatt-scale proton exchange membrane water electrolyzer (PEMWE) technology necessitates development of an efficient oxygen evolution catalyst with low cost and long lifetime. Currently, the stability of the most active iridium (Ir) catalysts is impaired by dissolution, redeposition, detachment, and agglomeration of Ir species. Here we present a ripening-induced embedding strategy that securely embeds the Ir catalyst in a cerium oxide support. Cryogenic electron tomography and all-atom kinetic Monte Carlo simulations reveal that synchronizing the growth rate of the support with the nucleation rate of Ir, regulated by sonication, is pivotal for successful synthesis. A PEMWE using this catalyst achieves a cell voltage of 1.72 volts at a current density of 3 amperes per square centimeter with an Ir loading of just 0.3 milligrams per square centimeter and a voltage degradation rate of 1.33 microvolts per hour, as demonstrated by a 6000-hour accelerated aging test.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AMulti-Layers Information Fused Deep Architecture for Skin Cancer Classification in Smart Healthcare

引用

computers, Materials & Continua 2025年第6期83卷 5299-5321页

作者： Veena Dillshad Muhammad Attique Khan Muhammad Nazir Jawad Ahmad Dina Abdulaziz AlHammadi Taha Houda Hee-Chan Cho Byoungchol Chang Department of Computer Science HITEC UniversityTaxila47080Pakistan Department of Artificial Intelligence College of Computer Engineering and SciencePrince Mohammad Bin Fahd UniversityAl-Khobar31952Saudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Center for Computational Social Science Hanyang UniversitySeoul01000Republic of Korea Department of Computer Science Hanynag UniversitySeoul01000Republic of Korea

Globally,skin cancer is a prevalent form of malignancy,and its early and accurate diagnosis is critical for patient *** evaluation of skin lesions is essential,but several challenges,such as long waiting times and subjective interpretations,make this task *** recent advancement of deep learning in healthcare has shownmuch success in diagnosing and classifying skin cancer and has assisted dermatologists in *** learning improves the speed and precision of skin cancer diagnosis,leading to earlier prediction and *** this work,we proposed a novel deep architecture for skin cancer classification in innovative *** proposed framework performed data augmentation at the first step to resolve the imbalance issue in the selected *** proposed architecture is based on two customized,innovative Convolutional neural network(CNN)models based on small depth and filter *** the first model,four residual blocks are added in a squeezed fashion with a small filter *** the second model,five residual blocks are added with smaller depth and more useful weight information of the lesion *** make models more useful,we selected the hyperparameters through Bayesian Optimization,in which the learning rate is *** training the proposed models,deep features are extracted and fused using a novel information entropy-controlled Euclidean Distance *** final features are passed on to the classifiers,and classification results are ***,the proposed trained model is interpreted through LIME-based localization on the HAM10000 *** experimental process of the proposed architecture is performed on two dermoscopic datasets,HAM10000 and *** obtained an improved accuracy of 90.8%and 99.3%on these datasets,***,the proposed architecture returned 91.6%for the cancer *** conclusion,the proposed architecture accuracy is compared with several pre-trained and state-of-the-art

关键词： Smart health skin cancer internet of things deep learning residual blocks fusion optimization

来源：评论

学校读者我要写书评

暂无评论

GESUBNET: GENE INTERACTION INFERENCE FOR DISEASE SUBTYPE NETWORK GENERATION

arXiv

引用

arXiv 2024年

作者： Yang, Ziwei Chen, Zheng Liu, Xin Kotoge, Rikuto Chen, Peng Matsubara, Yasuko Sakurai, Yasushi Sun, Jimeng Bioinformatics Center Kyoto University Japan SANKEN Osaka University Japan Japan RIKEN Center for Computational Science Japan Department of Computer Science University of Illinois Urbana-Champaign United States

Retrieving gene functional networks from knowledge databases presents a challenge due to the mismatch between disease networks and subtype-specific variations. Current solutions, including statistical and deep learning methods, often fail to effectively integrate gene interaction knowledge from databases or explicitly learn subtype-specific interactions. To address this mismatch, we propose GeSubNet, which learns a unified representation capable of predicting gene interactions while distinguishing between different disease subtypes. Graphs generated by such representations can be considered subtype-specific networks. GeSubNet is a multi-step representation learning framework with three modules: First, a deep generative model learns distinct disease subtypes from patient gene expression profiles. Second, a graph neural network captures representations of prior gene networks from knowledge databases, ensuring accurate physical gene interactions. Finally, we integrate these two representations using an inference loss that leverages graph generation capabilities, conditioned on the patient separation loss, to refine subtype-specific information in the learned representation. GeSubNet consistently outperforms traditional methods, with average improvements of 30.6%, 21.0%, 20.1%, and 56.6% across four graph evaluation metrics, averaged over four cancer datasets. Particularly, we conduct a biological simulation experiment to assess how the behavior of selected genes from over 11,000 candidates affects subtypes or patient distributions. The results show that the generated network has the potential to identify subtype-specific genes with an 83% likelihood of impacting patient distribution shifts. © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

scDrug: From single-cell RNA-seq to drug response prediction

引用

computational and Structural Biotechnology Journal 2023年 21卷 150-157页

作者： Hsieh, Chiao-Yu Wen, Jian-Hung Lin, Shih-Ming Tseng, Tzu-Yang Huang, Jia-Hsin Huang, Hsuan-Cheng Juan, Hsueh-Fen Taiwan AI Labs Taipei10351 Taiwan Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taipei11221 Taiwan Department of Life Science National Taiwan University Taipei10617 Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei10617 Taiwan Center for Computational and Systems Biology National Taiwan University Taipei10617 Taiwan

Single-cell RNA sequencing (scRNA-seq) technology allows massively parallel characterization of thousands of cells at the transcriptome level. scRNA-seq is emerging as an important tool to investigate the cellular components and their interactions in the tumor microenvironment. scRNA-seq is also used to reveal the association between tumor microenvironmental patterns and clinical outcomes and to dissect cell-specific effects of drug treatment in complex tissues. Recent advances in scRNA-seq have driven the discovery of biomarkers in diseases and therapeutic targets. Although methods for prediction of drug response using gene expression of scRNA-seq data have been proposed, an integrated tool from scRNA-seq analysis to drug discovery is required. We present scDrug as a bioinformatics workflow that includes a one-step pipeline to generate cell clustering for scRNA-seq data and two methods to predict drug treatments. The scDrug pipeline consists of three main modules: scRNA-seq analysis for identification of tumor cell subpopulations, functional annotation of cellular subclusters, and prediction of drug responses. scDrug enables the exploration of scRNA-seq data readily and facilitates the drug repurposing process. scDrug is freely available on GitHub at https://***/ailabstw/scDrug. © 2022 The Authors

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

Modularity-based selection of the number of slices in temporal network clustering

arXiv

引用

arXiv 2023年

作者： Seiron, Patrik Lindegren, Axel Magnani, Matteo Rohner, Christian Murata, Tsuyoshi Holme, Petter Department of Information Technology Uppsala University Sweden Department of Computer Science Tokyo Institute of Technology Japan Department of Computer Science Aalto University Finland Center for Computational Social Science Kobe University Japan

A popular way to cluster a temporal network is to transform it into a sequence of networks, also called slices, where each slice corresponds to a time interval and contains the vertices and edges existing in that interval. A reason to perform this transformation is that after a network has been sliced, existing algorithms designed to find clusters in multilayer networks can be used. However, to use this approach, we need to know how many slices to generate. This chapter discusses how to select the number of slices when generalized modularity is used to identify the clusters. Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Systems-based approaches to study immunometabolism

引用

Cellular & Molecular Immunology 2022年第3期19卷 409-420页

作者： Vinee Purohit Allon Wagner Nir Yosef Vijay K.Kuchroo Evergrande Center for Immunologic Diseases and Ann Romney Center for Neurologic Diseases Brigham and Women’s HospitalHarvard Medical SchoolBostonMA02115USA Broad Institute of MIT and Harvard CambridgeMA02141USA Department of Electrical Engineering and Computer Science University of CaliforniaBerkeleyCA94720USA Center for Computational Biology University of CaliforniaBerkeleyCA94720USA

Technical advances at the interface of biology and computation,such as single-cell RNA-sequencing(scRNA-seq),reveal new layers of complexity in cellular *** emerging area of investigation using the systems biology approach is the study of the metabolism of immune *** diverse spectra of immune cell phenotypes,sparsity of immune cell numbers in vivo,limitations in the number of metabolites identified,dynamic nature of cellular metabolism and metabolic fluxes,tissue specificity,and high dependence on the local milieu make investigations in immunometabolism challenging,especially at the single-cell *** this review,we define the systemic nature of immunometabolism,summarize cell-and system-based approaches,and introduce mathematical modeling approaches for systems interrogation of metabolic changes in immune *** close the review by discussing the applications and shortcomings of metabolic modeling *** systems-oriented studies of metabolism expected to become a mainstay of immunological research,an understanding of current approaches toward systems immunometabolism will help investigators make the best use of current resources and push the boundaries of the discipline.

关键词： Immunometabolism Metabolic techniques GSMM Metabolic modeling Systems biology

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：