个人简介
博士,副教授,博士生导师。
主要研究方向为机器学习、AI4Science、深度学习理论、多模态大模型等。
教育简历
2005年毕业于北京工业大学,获计算机应用技术专业博士学位。
2000年毕业于北京工业大学,获理论物理专业硕士学位。
工作履历
2010.10-2011.10 美国华盛顿大学(University of Washington, Seattle)计算机科学与工程系 访问学者。
2008.12- 北京工业大学 副教授。
2005.05-2008.11 北京工业大学 讲师。
课程教学
本科生课程:数字图像处理。
研究生课程:最优化理论与算法。
博士生课程:深度学习中的优化理论前沿。
科研项目
主持国家自然科学基金项目、北京市教委科技计划项目等纵向项目及多项横向项目。近五年到校经费近800万元。
主要论文论著
(1) Tongtong Yuan; Xuange Zhang; Kun Liu; Bo Liu*; Chen Chen; Jian Jin; Zhenzhen Jiao. Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges. IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), Seattle, USA, 2024
(2) Bo Liu. Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations. IEEE Transactions on Neural Networks and Learning Systems, 35(4),2024,5382 – 5394
(3) Tongtong Yuan, Xuange Zhang, Bo Liu*, Kun Liu, Jian Jin, Zhenzhen Jiao. Surveillance Video-and-Language Understanding: from Small to Large Multimodal Models. IEEE Transactions on Circuits and Systems for Video Technology, 2024, DOI: 10.1109/TCSVT.2024.3462433
(4) Tongtong Yuan; Zulin Li; Bo Liu*; Yinan Tang; Yujia Liu. ARPruning: An automatic channel pruning based on attention map ranking. Neural Networks, 174, 2024,DOI: 10.1016/j.neunet.2024.106220
(5) Bo Liu; Mengya Shen. Some Geometrical and Topological Properties of DNNs' Decision Boundaries. Theoretical Computer Science, 2022, 908: 64-75
(6) Bo Liu; Zhaoying Liu; Ting Zhang; Tongtong Yuan. Non-differentiable saddle points and sub-optimal local minima exist for deep ReLU networks. Neural Networks, 2021, 144(12): 75- 89
(7) Bo Liu. Understanding the loss landscape of one-hidden-layer ReLU networks. Knowledge Based Systems, 2021, 220(5): 1-11
(8) Bo Liu; Yi Liang. Optimal function approximation with ReLU neural networks. Neurocomputing, 2021, 435(5): 216-227
(9) Li Yujian; Liu Bo; Yang Xinwu; Fu Yaozong; Li Houjun. Multiconlitron: A General Piecewise Linear Classifier. IEEE Transactions on Neural Networks, 2011, 22(2): 276-289
(10) Li Yujian; Liu Bo. A normalized Levenshtein distance metric. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1091-1095