CASIA OpenIR

Browse/Search Results:  1-4 of 4 Help

Filters    
Selected(0)Clear Items/Page:    Sort:
基于情境信号的连续多任务学习 学位论文
, 北京: 中国科学院大学, 2019
Authors:  曾冠雄
Adobe PDF(4369Kb)  |  Favorite  |  View/Download:167/6  |  Submit date:2019/06/04
前额叶皮层  正交权重修改  情境依赖处理  灾难性遗忘  连续学习  多任务学习  
人工神经网络中连续学习与情境学习的算法设计与研究 研究报告
2019
Authors:  陈阳
Adobe PDF(2342Kb)  |  Favorite  |  View/Download:84/1  |  Submit date:2019/05/09
类脑智能,连续学习,情境学习,正交权重修改算法,情境信息处理模块  
Guided Policy Search for Sequential Multitask Learning 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2019, 卷号: 49, 期号: 1, 页码: 216-226
Authors:  Xiong, Fangzhou;  Sun, Biao;  Yang, Xu;  Qiao, Hong;  Huang, Kaizhu;  Hussain, Amir;  Liu, Zhiyong
View  |  Adobe PDF(1059Kb)  |  Favorite  |  View/Download:55/1  |  Submit date:2019/07/12
Elastic weight consolidation (EWC)  guided policy search (GPS)  reinforcement learning (RL)  sequential multitask learning  
Primitives Generation Policy Learning without Catastrophic Forgetting for Robotic Manipulation 会议论文
, China National Convention Center (CNCC), Beijing, November 8-11, 2019
Authors:  Fangzhou Xiong;  Zhiyong Liu;  Kaizhu Huang;  Xu Yang;  Amir Hussain
View  |  Adobe PDF(277Kb)  |  Favorite  |  View/Download:28/6  |  Submit date:2020/04/26