个人简介
刘潇,男,博士,讲师,2023年获得南京大学博士学位。2023年9月起在必赢bwin线路检测中心从教至今,主要研究人工智能和机器学习方法,具体研究兴趣包括可解释人工智能、强化学习、模型轻量化等。
欢迎对研究人工智能有热情,希望探索前沿的同学,一同在这个充满挑战与机遇的领域创造未来!
一、主讲课程
无
二、国内外学术期刊发表文章
l Chen Wubin, Li Wenbin, Liu Xiao, Yang Shangdong, Gao Yang*. Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient, Proceedings of the AAAI Conference on Artificial Intelligence. 2023. (CCF A)
l Liu Xiao, Liu Shuyang, An Bo, Gao Yang*, Li Wenbin. Effective Interpretable Policy Distillation via Critical Experience Point Identification. IEEE Intelligent Systems. 2023. (JCR Q1)
l 刘潇,刘书洋,庄韫恺,高阳*. 强化学习可解释性基础问题探索和方法综述. 软件学报. 2023, 34(5): 2300-2316. (CCF-A)
l Liu Xiao, Li Wenbin, Huo Jing, Gao Yang*. Layerwise sparse coding for pruned deep neural networks with extreme compression ratio. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2020, 34(04): 4900-4907. (CCF-A)
l Liu Xiao, Zhou Bin. DMS: a Dynamic Multi-tiered Storage with Deduplication Based on Variable-Sized Chunks. 2017 6th International Conference on Computer Science and Network Technology (ICCSNT). IEEE, 2017: 127-131. (EI)
三、联系方式
通信地址:湖南省湘潭市雨湖区湘潭大学工科楼S610
邮编:411105
电子邮箱:liuxiao730@outlook.com