CASIA OpenIR

浏览/检索结果: 共6条,第1-6条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
基于视觉表征的深度强化学习方法 学位论文
, 2024
作者:  刘民颂
Adobe PDF(10778Kb)  |  收藏  |  浏览/下载:41/4  |  提交时间:2024/06/22
深度强化学习,视觉表征学习,自监督学习,状态抽象,Transformer神经网络  
Aggregating Randomized Clustering-Promoting Invariant Projections for Domain Adaptation 期刊论文
IEEE Trans. Pattern Anal. Machine Intell., 2019, 卷号: 41, 期号: 5, 页码: 1027-1042
作者:  Jian Liang;  Ran He;  Zhenan Sun;  Tieniu Tan
浏览  |  Adobe PDF(865Kb)  |  收藏  |  浏览/下载:451/149  |  提交时间:2019/06/10
Unsupervised Domain Adaptation  Domain-invariant Projection  Class-clustering  Sampling-and-fusion  
Building Energy Consumption Prediction: An Extreme Deep Learning Approach 期刊论文
ENERGIES, 2017, 卷号: 10, 期号: 10, 页码: 1-20
作者:  Li, Chengdong;  Ding, Zixiang;  Zhao, Dongbin;  Yi, Jianqiang;  Zhang, Guiqing
浏览  |  Adobe PDF(1918Kb)  |  收藏  |  浏览/下载:342/55  |  提交时间:2017/12/30
Building Energy Consumption  Deep Learning  Stacked Autoencoders  Extreme Learning Machine  
Parameter Identifiability in Statistical Machine Learning: A Review 期刊论文
NEURAL COMPUTATION, 2017, 卷号: 29, 期号: 5, 页码: 1151-1203
作者:  Ran, Zhi-Yong;  Hu, Bao-Gang
浏览  |  Adobe PDF(466Kb)  |  收藏  |  浏览/下载:350/110  |  提交时间:2017/07/18
Parameter Identifiability  Statistical Machine Learning  
Biologically Inspired Model for Visual Cognition Achieving Unsupervised Episodic and Semantic Feature Learning 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 卷号: 46, 期号: 10, 页码: 2335-2347
作者:  Qiao, Hong;  Li, Yinlin;  Li, Fengfu;  Xi, Xuanyang;  Wu, Wei
浏览  |  Adobe PDF(2781Kb)  |  收藏  |  浏览/下载:485/159  |  提交时间:2016/06/21
Biologically Inspired  Hierarchical Model  Key Components Learning  Semantic Description  
Enhanced HMAX model with feedforward feature learning for multiclass categorization 期刊论文
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2015, 卷号: 9, 页码: 1-14
作者:  Li, Yinlin;  Wu, Wei;  Zhang, Bo;  Li, Fengfu
浏览  |  Adobe PDF(3664Kb)  |  收藏  |  浏览/下载:396/89  |  提交时间:2016/03/30
Hmax  Biologically Inspired  Feedforward  Saliency Map  Middle Level Patch Learning  Feature Encoding  Multiclass Categorization