中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共14条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
A comprehensive review of image retargeting 期刊论文
NEUROCOMPUTING, 2024, 卷号: 579, 页码: 18
作者:  Fan, Xiaoting;  Zhang, Zhong;  Sun, Long;  Xiao, Baihua;  Durrani, Tariq S.
收藏  |  浏览/下载：42/0  |  提交时间：2024/05/30
Image retargeting  Stereoscopic image  Discrete method  Continuous method  Deep learning  
Data-efficient model-based reinforcement learning with trajectory discrimination 期刊论文
COMPLEX & INTELLIGENT SYSTEMS, 2023, 页码: 10
作者:  Qu, Tuo;  Duan, Fuqing;  Zhang, Junge;  Zhao, Bo;  Huang, Wenzhen
收藏  |  浏览/下载：133/0  |  提交时间：2023/11/16
Reinforcement learning  Deep learning  Continuous control task  World model  
BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search 期刊论文
IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS: SYSTEMS, 2022, 卷号: 0, 期号: 0, 页码: 0
作者:  Zixiang, Ding;  Yaran, Chen;  Nannan, Li;  Dongbin, Zhao
Adobe PDF(7657Kb)  |  收藏  |  浏览/下载：234/64  |  提交时间：2022/01/07
Broad neural architecture search (BNAS), continuous relaxation, confident learning rate, partial channel connections, image classification.  
Adaptive Critic Designs for Optimal Event-Driven Control of a CSTR System 期刊论文
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 卷号: 17, 期号: 1, 页码: 484-493
作者:  Yang, Xiong;  Wei, Qinglai
收藏  |  浏览/下载：187/0  |  提交时间：2021/01/06
Chemical reactors  Optimal control  Nonlinear systems  Adaptive systems  Cost function  Informatics  Closed loop systems  Adaptive critic designs (ACDs)  continuous stirred tank reactor (CSTR)  discounted cost  event-driven control  reinforcement learning (RL)  
A Study of Personal Recognition Method Based on EMG Signal 期刊论文
IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS, 2020, 卷号: 14, 期号: 4, 页码: 681-691
作者:  Lu, Lijing;  Mao, Jingna;  Wang, Wuqi;  Ding, Guangxin;  Zhang, Zhiwei
Adobe PDF(3835Kb)  |  收藏  |  浏览/下载：348/60  |  提交时间：2020/09/28
Electromyography  personal identification  personal verification  discrete wavelet transform  ExtraTreesClassifer  continuous wavelet transform  convolutional neural networks  transfer learning  siamese network  
DID: Disentangling-Imprinting-Distilling for Continuous Low-Shot Detection 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 7765-7778
作者:  Chen, Xianyu;  Wang, Yali;  Liu, Jianzhuang;  Qiao, Yu
收藏  |  浏览/下载：183/0  |  提交时间：2020/08/21
Object detection  low-shot learning  continuous learning  deep learning  transfer learning  
Incremental Adaptive Learning Vector Quantization for Character Recognition with Continuous Style Adaptation 期刊论文
COGNITIVE COMPUTATION, 2018, 卷号: 10, 期号: 2, 页码: 334-346
作者:  Shen, Yuan-Yuan;  Liu, Cheng-Lin
Adobe PDF(1575Kb)  |  收藏  |  浏览/下载：302/85  |  提交时间：2018/10/10
Continuous Incremental Adaptive Learning Vector Quantization  Style Transfer Mapping  Local Style Consistency  Active Learning  
Adaptive near-optimal controllers for non-linear decentralised feedback stabilisation problems 期刊论文
IET CONTROL THEORY AND APPLICATIONS, 2017, 卷号: 11, 期号: 6, 页码: 799-806
作者:  Wang, Ding;  He, Haibo;  Zhao, Bo;  Liu, Derong
Adobe PDF(3178Kb)  |  收藏  |  浏览/下载：374/107  |  提交时间：2017/07/18
Adaptive Control  Optimal Control  Continuous Time Systems  Nonlinear Control Systems  Decentralised Control  Feedback  Stability  Control System Synthesis  Adaptive-critic-based Near-optimal Controller  Continuous-time Nonlinear Decentralised Feedback Stabilisation Problem  Decentralised Feedback Control Problem  Updating Rule  Approximation Property  Learning Mechanism  
Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics 期刊论文
IET CONTROL THEORY AND APPLICATIONS, 2016, 卷号: 10, 期号: 12, 页码: 1339-1347
作者:  Zhu, Yuanheng;  Zhao, Dongbin;  Li, Xiangjun
浏览  |  Adobe PDF(976Kb)  |  收藏  |  浏览/下载：449/183  |  提交时间：2016/12/26
Nonlinear Control Systems  Continuous Time Systems  Learning (Artificial Intelligence)  Optimal Control  Dynamic Programming  Lyapunov Methods  Linear Systems  Reinforcement Learning  Continuous-time Problem  Nonlinear Optimal Tracking Problem  Adaptive Dynamic Programming  Model-free Adaptive Optimal Tracking Algorithm  Lyapunov Analysis  Linear System  
连续状态空间的强化学习问题 学位论文
, 中国科学院自动化研究所: 中国科学院研究生院, 2007
作者:  何源
Adobe PDF(2826Kb)  |  收藏  |  浏览/下载：445/0  |  提交时间：2015/09/02
强化学习  连续状态空间  核方法  函数逼近  Reinforcement Learning  Continuous State Space  Kernel Method  Function