CASIA OpenIR

浏览/检索结果: 共17条,第1-10条 帮助

限定条件        
已选(0)清除 条数/页:   排序方式:
Vision-based control in the open racing car simulator with deep and reinforcement learning 期刊论文
Journal of Ambient Intelligence and Humanized Computing, 2019, 页码: doi={10.1007/s12652-019-01503-y}
作者:  Yuanheng Zhu;  Dongbin Zhao
Adobe PDF(2210Kb)  |  收藏  |  浏览/下载:64/17  |  提交时间:2023/04/26
Performance Evaluation and Improvement of Chipset Assembly & Test Production Line Based on Variability 期刊论文
International Journal of Automation and Computing, 2019, 卷号: 16, 期号: 2, 页码: 186-198
作者:  Chang-Jun Li;  Zong-Shi Xie;  Xin-Ran Peng;  Bo Li
浏览  |  Adobe PDF(1239Kb)  |  收藏  |  浏览/下载:157/49  |  提交时间:2021/02/22
Performance evaluation and improvement  chipset assembly & test production line (CATPL)  parameters  Little′s law  variability.  
Synchronous Bidirectional Neural Machine Translation 期刊论文
Transactions of Association for Computational Linguistics (TACL), 2019, 期号: Vol. 7, 页码: pp. 91-105
作者:  Zhou, Long;  Zhang, Jiajun;  Zong, Chenqqing
Adobe PDF(1189Kb)  |  收藏  |  浏览/下载:180/50  |  提交时间:2020/06/23
Neural machine translation, bidirectional decoding  
Connecting Model-Based and Model-Free Control With Emotion Modulation in Learning Systems 期刊论文
IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 卷号: 10, 期号: 4, 页码: 1-15
作者:  Huang, Xiao;  Wu, Wei;  Qiao, Hong
Adobe PDF(1614Kb)  |  收藏  |  浏览/下载:300/100  |  提交时间:2020/06/09
Brain-inspired computing  decision-making  emotion modulation  emotion-cognition interactions  reinforcement learning  
Actor-Critic-Identifier Structure-Based Decentralized Neuro-Optimal Control of Modular Robot Manipulators With Environmental Collisions 期刊论文
IEEE ACCESS, 2019, 卷号: 7, 页码: 96148-96165
作者:  Dong, Bo;  An, Tianjiao;  Zhou, Fan;  Liu, Keping;  Yu, Weibo;  Li, Yuanchun
收藏  |  浏览/下载:294/0  |  提交时间:2019/12/16
Adaptive dynamic programming  collision identification  decentralized optimal control  modular robot manipulators  zero-sum game  
Towards Real-Time Advancement of Underwater Visual Quality With GAN 期刊论文
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2019, 卷号: 66, 期号: 12, 页码: 9350-9359
作者:  Chen, Xingyu;  Yu, Junzhi;  Kong, Shihan;  Wu, Zhengxing;  Fang, Xi;  Wen, Li
浏览  |  Adobe PDF(4984Kb)  |  收藏  |  浏览/下载:487/159  |  提交时间:2019/12/16
Generative adversarial networks (GAN) image restoration  machine learning  underwater vision  
Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 10, 页码: 5105-5120
作者:  Li, Debang;  Wu, Huikai;  Zhang, Junge;  Huang, Kaiqi
Adobe PDF(6588Kb)  |  收藏  |  浏览/下载:403/46  |  提交时间:2019/12/16
Reinforcement learning  adversarial learning  image cropping  
Deep Multi-Modality Adversarial Networks for Unsupervised Domain Adaptation 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 9, 页码: 2419-2431
作者:  Ma, Xinhong;  Zhang, Tianzhu;  Xu, Changsheng
Adobe PDF(2142Kb)  |  收藏  |  浏览/下载:382/49  |  提交时间:2019/12/16
Unsupervised domain adaptation  triplet loss  stacked attention  multi-modality  social event recognition  
Output Tracking Control Based on Adaptive Dynamic Programming With Multistep Policy Evaluation 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2019, 卷号: 49, 期号: 10, 页码: 2155-2165
作者:  Luo, Biao;  Liu, Derong;  Huang, Tingwen;  Liu, Jiangjiang
收藏  |  浏览/下载:256/0  |  提交时间:2019/12/16
Adaptive dynamic programming (ADP)  Bellman equation  heuristic dynamic programming  neural networks (NNs)  output tracking control  
Decentralized robust zero-sum neuro-optimal control for modular robot manipulators in contact with uncertain environments: theory and experimental verification 期刊论文
NONLINEAR DYNAMICS, 2019, 卷号: 97, 期号: 1, 页码: 503-524
作者:  Dong, Bo;  An, Tianjiao;  Zhou, Fan;  Liu, Keping;  Li, Yuanchun
收藏  |  浏览/下载:263/0  |  提交时间:2019/12/16
Modular robot manipulators  Adaptive dynamic programming  Decentralized control  Optimal control  Zero-sum game