咨询与建议

限定检索结果

文献类型

  • 8,558 篇 会议
  • 4,642 篇 期刊文献
  • 8 篇 学位论文
  • 2 篇 资讯
  • 1 册 图书

馆藏范围

  • 13,211 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 12,753 篇 工学
    • 11,929 篇 计算机科学与技术...
    • 9,528 篇 软件工程
    • 1,726 篇 生物工程
    • 1,639 篇 信息与通信工程
    • 1,457 篇 控制科学与工程
    • 1,208 篇 电气工程
    • 591 篇 生物医学工程(可授...
    • 350 篇 机械工程
    • 340 篇 光学工程
    • 327 篇 电子科学与技术(可...
    • 305 篇 化学工程与技术
    • 232 篇 安全科学与工程
    • 203 篇 动力工程及工程热...
    • 181 篇 仪器科学与技术
    • 142 篇 土木工程
  • 5,687 篇 理学
    • 3,337 篇 数学
    • 1,902 篇 生物学
    • 1,289 篇 统计学(可授理学、...
    • 791 篇 物理学
    • 669 篇 系统科学
    • 243 篇 化学
  • 2,183 篇 管理学
    • 1,360 篇 图书情报与档案管...
    • 885 篇 管理科学与工程(可...
    • 441 篇 工商管理
  • 673 篇 医学
    • 522 篇 基础医学(可授医学...
    • 517 篇 临床医学
    • 307 篇 药学(可授医学、理...
  • 338 篇 法学
    • 320 篇 社会学
  • 191 篇 教育学
    • 181 篇 教育学
  • 158 篇 经济学
    • 153 篇 应用经济学
  • 141 篇 农学
  • 81 篇 文学
  • 15 篇 艺术学
  • 13 篇 军事学
  • 3 篇 哲学
  • 1 篇 历史学

主题

  • 13,211 篇 learning algorit...
  • 101 篇 neural networks
  • 91 篇 learning
  • 71 篇 machine learning
  • 59 篇 neural network
  • 49 篇 algorithms
  • 32 篇 artificial intel...
  • 29 篇 learning (artifi...
  • 26 篇 learning systems
  • 26 篇 network models
  • 26 篇 classification
  • 26 篇 reward
  • 26 篇 classifiers
  • 24 篇 iterative method...
  • 24 篇 game theory
  • 24 篇 artificial neura...
  • 23 篇 optimization
  • 22 篇 dataset
  • 21 篇 reinforcement le...
  • 19 篇 converge

机构

  • 37 篇 university of ca...
  • 37 篇 stanford univers...
  • 32 篇 carnegie mellon ...
  • 30 篇 google research ...
  • 29 篇 uc berkeley unit...
  • 27 篇 carnegie mellon ...
  • 25 篇 columbia univers...
  • 24 篇 mit united state...
  • 24 篇 microsoft resear...
  • 23 篇 university colle...
  • 22 篇 massachusetts in...
  • 22 篇 deepmind united ...
  • 22 篇 google research
  • 21 篇 tsinghua univers...
  • 20 篇 princeton univer...
  • 20 篇 cornell universi...
  • 19 篇 deepmind
  • 18 篇 university of pe...
  • 18 篇 mit cambridge ma...
  • 18 篇 microsoft resear...

作者

  • 23 篇 mohri mehryar
  • 21 篇 levine sergey
  • 20 篇 tao dacheng
  • 19 篇 liu yang
  • 15 篇 moran shay
  • 14 篇 zhou zhi-hua
  • 14 篇 krause andreas
  • 14 篇 jin rong
  • 14 篇 mansour yishay
  • 14 篇 wang wei
  • 14 篇 precup doina
  • 13 篇 hanneke steve
  • 13 篇 bengio yoshua
  • 12 篇 liu tongliang
  • 11 篇 yang qiang
  • 11 篇 pontil massimili...
  • 11 篇 daumé hal
  • 11 篇 sun wen
  • 11 篇 silver david
  • 11 篇 diakonikolas ili...

语言

  • 12,815 篇 英文
  • 239 篇 其他
  • 98 篇 中文
  • 16 篇 法文
  • 14 篇 土耳其文
  • 7 篇 德文
  • 6 篇 西班牙文
  • 6 篇 日文
  • 5 篇 朝鲜文
  • 4 篇 俄文
  • 3 篇 葡萄牙文
  • 1 篇 乌克兰文
检索条件"主题词=Learning algorithms"
13211 条 记 录,以下是4871-4880 订阅
排序:
Contextual-Bandit based MIMO Relay Selection Policy with Channel Uncertainty
Contextual-Bandit based MIMO Relay Selection Policy with Cha...
收藏 引用
IEEE International Conference on Communications (IEEE ICC) / Workshop on NOMA for 5G and Beyond
作者: Gupta, Ankit Balasubramanya, Naveen Mysore Sellathurai, Mathini Heriot Watt Univ HWU Sch Engn & Phys Sci Edinburgh Midlothian Scotland Indian Inst Technol Dept Elect Engn Dharwad Karnataka India
In this work, we exploit the potential benefits of multi-arm bandit scheme in cooperative multiple-input multiple output (MIMO) wireless networks. In particular, we consider an online-policy for amplify-and-forward MI... 详细信息
来源: 评论
Human-robot Interaction Control by using a General Sensory Model  16
Human-robot Interaction Control by using a General Sensory M...
收藏 引用
16th IEEE International Conference on Control and Automation (ICCA)
作者: Lyu, Shangke Cheah, Chien Chern Yu, Xiang Guo, Lei Beihang Univ Hangzhou Innovat Inst Hangzhou 310052 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore Beihang Univ Beijing 100191 Peoples R China
In recent years, there has been an increasing interest in the study of human-robot interactions (HRI). In HRI tasks, the strengths of both human and robot can be utilized in task execution in a complimentary way. Acco... 详细信息
来源: 评论
"Other-Play" for Zero-Shot Coordination  37
"Other-Play" for Zero-Shot Coordination
收藏 引用
International Conference on Machine learning (ICML)
作者: Hu, Hengyuan Lerer, Adam Peysakhovich, Alex Foerster, Jakob Facebook AI Res Menlo Pk CA 94025 USA
We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e.g. humans). Standard Multi-Agent Reinforcement learning (MARL) methods ty... 详细信息
来源: 评论
Realization algorithms of Major Types of Linguistic Processors Based on the Systems with Predefined Semantics
Realization Algorithms of Major Types of Linguistic Processo...
收藏 引用
Global Smart Industry Conference (GloSIC)
作者: Vanyulin, A. N. Zvereva, E. A. Lavina, T. A. Mochalova, T. A. Alekseeva, N. R. Chuvash State Univ Dept Computat Technol Cheboksary Russia South Ural State Univ NRU Dept Humanities Nat Sci & Tech Disciplines Branch City Nizhnevartovsk Nizhnevartovsk Russia
This paper discusses the main types of applications for natural language (NL) processing. Depending on the purpose of the semantic system, a natural language model is built. Based on this model an application is devel... 详细信息
来源: 评论
Leveraging Deep learning Techniques for Malaria Parasite Detection Using Mobile Application
收藏 引用
WIRELESS COMMUNICATIONS & MOBILE COMPUTING 2020年 第1期2020卷
作者: Masud, Mehedi Alhumyani, Hesham Alshamrani, Sultan S. Cheikhrouhou, Omar Ibrahim, Saleh Muhammad, Ghulam Hossain, M. Shamim Shorfuzzaman, Mohammad Taif Univ Coll Comp & Informat Technol At Taif 21974 Saudi Arabia Taif Univ Elect Engn Dept At Taif Saudi Arabia Cairo Univ Comp Engn Dept Cairo Egypt King Saud Univ Dept Comp Engn Coll Comp & Informat Sci Riyadh 11543 Saudi Arabia King Saud Univ Coll Comp & Informat Sci Dept Software Engn Riyadh 11543 Saudi Arabia
Malaria is a contagious disease that affects millions of lives every year. Traditional diagnosis of malaria in laboratory requires an experienced person and careful inspection to discriminate healthy and infected red ... 详细信息
来源: 评论
Research on diabetes prediction method based on electronic medical record data analysis
Research on diabetes prediction method based on electronic m...
收藏 引用
International Conference on Energy, Environment and Bioengineering (ICEEB)
作者: Chen Hui Wang Mingyuan Tang Dingjun Zhang Longwei Guo Ziyan Zhao Jun Zhejiang Univ Hangzhou 310058 Peoples R China Sichuan Univ Chengdu 610065 Peoples R China Dongguan Univ Technol Dongguan 523808 Peoples R China Shandong Univ Tradit Chinese Med Jinan 250355 Peoples R China
The continuous progress of computer science and technology has accelerated the pace of informatization construction of the medical system. Medical technology has developed rapidly in various research directions, and t... 详细信息
来源: 评论
Random Reshuffling is Not Always Better  34
Random Reshuffling is Not Always Better
收藏 引用
34th Conference on Neural Information Processing Systems (NeurIPS)
作者: De Sa, Christopher Cornell Univ Dept Comp Sci Ithaca NY 14853 USA
Many learning algorithms, such as stochastic gradient descent, are affected by the order in which training examples are used. It is generally believed that sampling the training examples without-replacement, also know... 详细信息
来源: 评论
Designing Collective Behavior for Construction of Containment Structures using Actuated Blocks  14
Designing Collective Behavior for Construction of Containmen...
收藏 引用
14th Annual IEEE International Systems Conference (SysCon)
作者: Magueta, Marcos P. B. Barros dos Santos, Sergio R. Cappabianco, Fabio A. M. Givigi, Sidney N. Univ Fed Sao Paulo Sci & Technol Inst Sao Jose Dos Campos SP Brazil Queens Univ Sch Comp Kingston ON Canada
This paper presents a decentralized learning algorithm for learning how to coordinate an automated team of actuated parts designed to build several types of structures specified by a user on a plane surface. The algor... 详细信息
来源: 评论
RD2: Reward Decomposition with Representation Disentanglement  34
RD<SUP>2</SUP>: Reward Decomposition with Representation Dis...
收藏 引用
34th Conference on Neural Information Processing Systems (NeurIPS)
作者: Lin, Zichuan Yang, Derek Zhao, Li Qin, Tao Yang, Guangwen Liu, Tieyan Tsinghua Univ Beijing Peoples R China Univ Calif San Diego San Diego CA USA Microsoft Res Redmond WA 98052 USA
Reward decomposition, which aims to decompose the full reward into multiple sub-rewards, has been proven beneficial for improving sample efficiency in reinforcement learning. Existing works on discovering reward decom... 详细信息
来源: 评论
PARAMETRIC GRAPH-BASED SEPARABLE TRANSFORMS FOR VIDEO CODING
PARAMETRIC GRAPH-BASED SEPARABLE TRANSFORMS FOR VIDEO CODING
收藏 引用
IEEE International Conference on Image Processing (ICIP)
作者: Egilmez, Hilmi E. Teke, Oguzhan Said, Amir Seregin, Vadim Karczewicz, Marta Qualcomm Technol Inc San Diego CA 92121 USA CALTECH Pasadena CA 91125 USA CALTECH Dept Elect Engn Pasadena CA 91125 USA
In many video coding systems, separable transforms (such as two-dimensional DCT-2) have been used to code block residual signals obtained after prediction. This paper proposes a parametric approach to build graph-base... 详细信息
来源: 评论