咨询与建议

限定检索结果

文献类型

  • 113 篇 期刊文献
  • 94 篇 会议
  • 2 篇 学位论文

馆藏范围

  • 209 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 191 篇 工学
    • 121 篇 计算机科学与技术...
    • 71 篇 电气工程
    • 33 篇 控制科学与工程
    • 26 篇 信息与通信工程
    • 16 篇 软件工程
    • 13 篇 仪器科学与技术
    • 10 篇 石油与天然气工程
    • 10 篇 环境科学与工程(可...
    • 8 篇 机械工程
    • 8 篇 材料科学与工程(可...
    • 6 篇 电子科学与技术(可...
    • 6 篇 化学工程与技术
    • 5 篇 力学(可授工学、理...
    • 5 篇 动力工程及工程热...
    • 4 篇 建筑学
    • 4 篇 土木工程
    • 4 篇 水利工程
    • 4 篇 航空宇航科学与技...
    • 3 篇 生物工程
    • 2 篇 光学工程
  • 34 篇 理学
    • 15 篇 物理学
    • 9 篇 化学
    • 8 篇 数学
    • 6 篇 生物学
    • 2 篇 地球物理学
  • 15 篇 管理学
    • 14 篇 管理科学与工程(可...
  • 13 篇 医学
    • 11 篇 临床医学
    • 4 篇 基础医学(可授医学...
  • 3 篇 农学
  • 2 篇 经济学
    • 2 篇 应用经济学
  • 1 篇 法学
  • 1 篇 文学

主题

  • 209 篇 training algorit...
  • 32 篇 neural network
  • 27 篇 artificial neura...
  • 15 篇 neural networks
  • 9 篇 particle swarm o...
  • 8 篇 artificial neura...
  • 6 篇 deep learning
  • 6 篇 neural nets
  • 6 篇 machine learning
  • 6 篇 training
  • 5 篇 modeling
  • 5 篇 feature extracti...
  • 5 篇 multilayer perce...
  • 5 篇 forecasting
  • 4 篇 generative adver...
  • 4 篇 process neural n...
  • 4 篇 quasi-newton met...
  • 4 篇 power quality di...
  • 4 篇 learning (artifi...
  • 4 篇 recurrent neural...

机构

  • 3 篇 hebei univ engn ...
  • 3 篇 univ dayton dept...
  • 2 篇 lab cent lyonnai...
  • 2 篇 joint inst nucl ...
  • 2 篇 assiut univ dept...
  • 2 篇 univ calif san d...
  • 2 篇 ivanovo state un...
  • 2 篇 univ dubrovnik d...
  • 2 篇 univ tokyo grad ...
  • 2 篇 shandong univ sc...
  • 2 篇 south china univ...
  • 2 篇 univ technol com...
  • 2 篇 forth inst appl ...
  • 1 篇 govt arts coll d...
  • 1 篇 stanford univ de...
  • 1 篇 rabdan acad fac ...
  • 1 篇 univ teknol petr...
  • 1 篇 iasbs dept chem ...
  • 1 篇 dalian ocean uni...
  • 1 篇 pt pln persero e...

作者

  • 6 篇 ninomiya hiroshi
  • 5 篇 xu shaohua
  • 3 篇 gong n
  • 3 篇 taha tarek m.
  • 3 篇 liu kun
  • 3 篇 paul dipjyoti
  • 3 篇 pantazis yannis
  • 3 篇 zeng xiaoqin
  • 3 篇 hasan raqibul
  • 3 篇 mahboubi shahrza...
  • 3 篇 ng wing w. y.
  • 3 篇 bertrand-krajews...
  • 3 篇 stylianou yannis
  • 3 篇 denoeux t
  • 3 篇 takamichi shinno...
  • 2 篇 stadnik a
  • 2 篇 vilovic ivan
  • 2 篇 subbotin s
  • 2 篇 chen chen
  • 2 篇 saito yuki

语言

  • 190 篇 英文
  • 13 篇 其他
  • 6 篇 中文
检索条件"主题词=Training algorithm"
209 条 记 录,以下是91-100 订阅
排序:
A training algorithm for SpikeProp Improving Stability of Learning Process
A Training Algorithm for SpikeProp Improving Stability of Le...
收藏 引用
International Joint Conference on Neural Networks (IJCNN)
作者: Wakamatsu, Toshiki Takase, Haruhiko Kawanaka, Hiroharu Tsuruoka, Shinji Mie Univ Grad Sch Engn Tsu Mie 514 Japan
In this paper, we aims to improve stability of learning processes by the SpikeProp algorithm. We proposed the method that reduce the increase of the error in learning processes. It repeats two steps: (1) original Spik... 详细信息
来源: 评论
A training method for SpikeProp without redundant spikes -Removing unnecessary sub-connections during training-  12
A training method for SpikeProp without redundant spikes -Re...
收藏 引用
12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)
作者: Nakayama, Takutoshi Matsumoto, Takashi Takase, Haruhiko Kawanaka, Hiroharu Tsuruoka, Shinji Mie Univ Grad Sch Engn Tsu Mie 5148507 Japan Mie Univ Tsu Mie 5148507 Japan
SpikeProp, which is proposed by Bohte and extended by Booij, is a type of multi-layer networks of spiking neurons. Our research group has proposed a training algorithm for SpikeProp without redundant output spikes. Ho... 详细信息
来源: 评论
Bandwidth Enhancement by Direct Coupled Antenna for WLAN/GPS/WiMax Applications and Feed Point Coordinate Analysis through ANN
收藏 引用
WIRELESS PERSONAL COMMUNICATIONS 2016年 第1期91卷 9-32页
作者: Ayub, Shahanaz Srivastava, Rajat Bundelkhand Inst Engn & Technol Jhansi Uttar Pradesh India
In the present work first of all the bandwidth of rectangular Microstrip antenna is enhanced by direct coupling at the operating frequency 2.4 GHz using IE3D software and then it is analyzed through IE3D simulation so... 详细信息
来源: 评论
A Novel Quasi-Newton-Based training Using Nesterov's Accelerated Gradient for Neural Networks  25th
A Novel Quasi-Newton-Based Training Using Nesterov's Acceler...
收藏 引用
25th International Conference on Artificial Neural Networks (ICANN)
作者: Ninomiya, Hiroshi Shonan Inst Technol Dept Informat Sci Fujisawa Kanagawa Japan
Neural networks have been recognized as a useful tool for the function approximation problems with high-nonlinearity [1]. training is the most important step in developing a neural network model. Gradient based algori... 详细信息
来源: 评论
Operational parameter impact and back propagation artificial neural network modeling for phosphate adsorption onto acid-activated neutralized red mud
收藏 引用
JOURNAL OF MOLECULAR LIQUIDS 2016年 第0期216卷 35-41页
作者: Ye, Jie Cong, Xiangna Zhang, Panyue Zeng, Guangming Hoffmann, Erhard Wu, Yan Zhang, Haibo Fang, Wei Hunan Univ Coll Environm Sci & Engn Changsha 410082 Hunan Peoples R China Hunan Univ Minist Educ Key Lab Environm Biol & Pollut Control Changsha 410082 Hunan Peoples R China Karlsruhe Inst Technol Dept Aquat Environm Engn D-76131 Karlsruhe Germany Karlsruhe Inst Technol Inst Appl Mat IAM WK D-76131 Karlsruhe Germany
In this research the combination of neutralization activation and acid activation processes was employed to improve the physicochemical characters of red mud. In order to better understand the phosphate adsorption beh... 详细信息
来源: 评论
Wavelet Neural Network with Random Wavelet Function Parameters
收藏 引用
INTERNATIONAL JOURNAL OF ENGINEERING 2017年 第10期30卷 1510-1516页
作者: Bazoobandi, H. Esfarayen Univ Technol Dept Comp Engn Esfarayen North Khorasan Iran
The training algorithm of Wavelet Neural Networks (WNN) is a bottleneck which impacts on the accuracy of the final WNN model. Several methods have been proposed for training the WNNs. From the perspective of our resea... 详细信息
来源: 评论
Application of Artificial Neural Networks for Modeling Drug Release from a Bicomponent Hydrogel System  20
Application of Artificial Neural Networks for Modeling Drug ...
收藏 引用
20th International Conference on System Theory, Control and Computing (ICSTCC)
作者: Dumitriu, Tiberius Dumitriu, Raluca Petronela Manta, Vasile Gheorghe Asachi Tech Univ Iasi Fac Automat Control & Comp Engn Iasi Romania Petru Poni Inst Macromol Chem Phys Chem Polymers Dept Iasi Romania
Artificial Neural Networks (ANNs) have been used as modeling tools for prediction of drug release patterns from bicomponent hydrogel systems based on poly(N-isopropylacrylamide) and sodium alginate. The process modeli... 详细信息
来源: 评论
A training method for SpikeProp without redundant spikes - Removing unnecessary sub-connections during training
A training method for SpikeProp without redundant spikes - R...
收藏 引用
International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery
作者: Takutoshi Nakayama Takashi Matsumoto Haruhiko Takase Hiroharu Kawanaka Shinji Tsuruoka Graduate School of Engineering Mie university Tsu Mie 514-8507 Mie university Tsu Mie 514-8507
SpikeProp, which is proposed by Bohte and extended by Booij, is a type of multi-layer networks of spiking neurons. Our research group has proposed a training algorithm for SpikeProp without redundant output spikes. Ho... 详细信息
来源: 评论
Memristor Crossbar Based Unsupervised training
Memristor Crossbar Based Unsupervised Training
收藏 引用
IEEE National Aerospace and Electronics Conference (NAECON)
作者: Hasan, Raqibul Taha, Tarek M. Univ Dayton Dept Elect & Comp Engn Dayton OH 45469 USA
Several big data applications are particularly focused on classification and clustering tasks. Robustness of such system depends on how well it can extract important features from the raw data. For big data processing... 详细信息
来源: 评论
Manhattan Rule training for Memristive Crossbar Circuit Pattern Classifiers  9
Manhattan Rule Training for Memristive Crossbar Circuit Patt...
收藏 引用
IEEE 9th International Symposium on Intelligent Signal Processing (WISP)
作者: Zamanidoost, Elham Bayat, Farnood M. Strukov, Dmitri Kataeva, Irina Univ Calif Santa Barbara Dept Elect & Comp Engn Santa Barbara CA 93106 USA Denso Corp Adv Res Div Komenoki Nisshin Japan
We investigated batch and stochastic Manhattan Rule algorithms for training multilayer perceptron classifiers implemented with memristive crossbar circuits. In Manhattan Rule training, the weights are updated only usi... 详细信息
来源: 评论