CASIA OpenIR

Browse/Search Results:  1-10 of 370 Help

Selected(0)Clear Items/Page:    Sort:
基于演化学习与对手策略的不完美信息博弈算法研究 学位论文
, 中国科学院自动化研究所: 中国科学院自动化研究所, 2021
Authors:  张蒙
Adobe PDF(2515Kb)  |  Favorite  |  View/Download:10/0  |  Submit date:2021/06/20
不完美信息博弈  德州扑克  演化学习  在线对手建模  种群策略集成  
面向数字图像的对抗攻击与防御算法研究 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2021
Authors:  王雨桐
Adobe PDF(8781Kb)  |  Favorite  |  View/Download:6/0  |  Submit date:2021/06/15
对抗样本  对抗攻击  防御  对抗训练  神经网络  
基于值分解优化的多智能体深度强化学习方法研究 学位论文
工程硕士, 中国科学院自动化研究所: 中国科学院自动化研究所, 2021
Authors:  王凌霄
Adobe PDF(13415Kb)  |  Favorite  |  View/Download:6/0  |  Submit date:2021/06/15
深度强化学习  多智能体系统  价值函数分解算法  图神经网络  
Improving One-Shot NAS with Shrinking-and-Expanding Supernet 期刊论文
Pattern Recognition, 2021, 卷号: 118, 期号: 0, 页码: 0
Authors:  Hu YM(胡一鸣)
Adobe PDF(1755Kb)  |  Favorite  |  View/Download:3/1  |  Submit date:2021/06/18
Neural architecture search  supernet  Search space shrinking  
Continuous-Time Distributed Policy Iteration for Multicontroller Nonlinear Systems 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2021, 卷号: 51, 期号: 5, 页码: 2372-2383
Authors:  Wei, Qinglai;  Li, Hongyang;  Yang, Xiong;  He, Haibo
Favorite  |  View/Download:2/0  |  Submit date:2021/06/07
Optimal control  Nonlinear systems  Decentralized control  Mathematical model  Convergence  Multi-agent systems  Adaptive dynamic programming (ADP)  approximate dynamic programming  distributed policy iteration  nonlinear systems  optimal control  
定量降水机器学习模型与方法研究 学位论文
中国科学院大学, 中国科学院自动化研究所: 中国科学院大学, 2021
Authors:  吴雅婧
Adobe PDF(11694Kb)  |  Favorite  |  View/Download:7/0  |  Submit date:2021/06/18
机器学习  定量降水估计  定量降水预报  深度图神经网络  时空图卷 积网络  
Consensus Control of Leader-Following Multi-Agent Systems in Directed Topology With Heterogeneous Disturbances 期刊论文
IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2021, 卷号: 8, 期号: 2, 页码: 423-431
Authors:  Wei, Qinglai;  Wang, Xin;  Zhong, Xiangnan;  Wu, Naiqi
Adobe PDF(4423Kb)  |  Favorite  |  View/Download:11/1  |  Submit date:2021/03/08
Consensus control  directed topology  external disturbance  multi-agent (MA) systems  
A partial policy iteration ADP algorithm for nonlinear neuro-optimal control with discounted total reward 期刊论文
NEUROCOMPUTING, 2021, 卷号: 424, 页码: 23-34
Authors:  Liang, Mingming;  Wei, Qinglai
Favorite  |  View/Download:37/0  |  Submit date:2021/03/15
Adaptive critic designs  Adaptive dynamic programming  Policy iteration  Neural networks  Neuro-dynamic programming  Nonlinear systems  Optimal control  
Object Reconstruction Based on Attentive Recurrent Network from Single and Multiple Images 期刊论文
NEURAL PROCESSING LETTERS, 2021, 期号: 53, 页码: 18
Authors:  Gao, Zishu;  Li, En;  Wang, Zhe;  Yang, Guodong;  Lu, Jiwu;  Ouyang, Bo;  Xu, Dawei;  Liang, Zize
Adobe PDF(1338Kb)  |  Favorite  |  View/Download:18/0  |  Submit date:2021/03/01
Object reconstruction  Convolutional LSTM  Visual attention  Robotic application  
2D and 3D Palmprint and Palm Vein Recognition Based on Neural Architecture Search 期刊论文
International Journal of Automation and Computing, 2021, 卷号: 18, 期号: 3, 页码: 377-409
Authors:  Wei Jia;  Wei Xia;  Yang Zhao;  Hai Min;  Yan-Xiang Chen
Adobe PDF(15758Kb)  |  Favorite  |  View/Download:5/0  |  Submit date:2021/05/24
Performance evaluation  neural architecture search  biometrics  palmprint  palm vein  deep learning