
楚浩宇,讲师,安徽蒙城人。2024年9月于北京交通大学信息科学研究所获得工学博士学位,师从韦世奎教授。2023年3月至2024年4月赴日本大阪大学公派访学一年,师从Yuto Miyatake与Furihata Daisuke教授。
主要研究方向包括深度神经网络设计、计算机视觉、科学机器学习等,发表国际人工智能顶级会议(CCF A类)论文2篇、SCI 期刊论文3篇,主持中央高校基本科研项目1项。
代表性成果:
Haoyu Chu, Yuto Miyatake, Wenjun Cui, Shikui Wei and Daisuke Furihata. Structure-preserving physics-informed neural networks with energy or Lyapunov structure[C]. Proceedings of the International Joint Conference on Artificial Intelligence. 2024: 3872-3880.(IJCAI-24,CCF A类会议论文)
Haoyu Chu, Shikui Wei, Ting Liu, Yao Zhao, and Yuto Miyatake. Lyapunov-stable deep equilibrium models[C]. Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(10): 11615-11623.(AAAI-24,CCF A类会议论文)
Haoyu Chu, Shikui Wei, Shunli Zhang, and Yao Zhao. TrapezoidalNet: A new network architecture inspired from the numerical solution of ordinary differential equations[J]. Alexandria Engineering Journal, 2023, 81: 55-63.(SCI期刊论文)
Haoyu Chu, Shikui Wei, Qiming Lu, and Yao Zhao. Improving neural ordinary differential equations via knowledge distillation[J]. IET Computer Vision, 2024, 18(2) : 304-314.(SCI期刊论文)
Email: 6784@cumt.edu.cn
