Computer Science Home |
ASAP |
Room: C79
Tel: (+44) (0) 115 84 66594
E-mail: heda.song@nottingham.ac.uk
I am a PhD student in Computer Science at the University of Nottingham. I do my research within the Computational Optimisation and Learning (COL) research group. My research interest covers the interactions between machine learning and optimisation, meta-learning and few-shot learning.
First supervisor: | Dr. Isaac Triguero |
Second supervisor: | Dr. Ender Özcan |
My research aims is to investigate meta-learning methods for few-shot learning problems.
Bachelor in Automation from Northeastern University(China), 2013.
Master in Control Theory and Control Engineering from Northeastern University(China), 2017. My Master thesis is about prediction and control of multivariate molten iron quality indices in blast furnace ironmaking processes.
Heda Song, Mercedes Torres Torres, Ender Özcan, Isaac Triguero, "L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout", Arxiv, 2019. | |
Li Zhang, Heda Song, Nikolaos Aletras, Haiping Lu, "Node-Feature Convolution for Graph Convolutional Networks", The 28th ACM International Conference on Information and Knowledge Management (CIKM), Graph Representation Learning and its Applications workshop, 2019. | |
Heda Song, Isaac Triguero, Ender Özcan, "A review on the self and dual interactions between machine learning and optimisation", Progress in Artificial Intelligence, 2019. | |
Ping Zhou, Heda Song, Hong Wang, Tianyou Chai, "Data-Driven Nonlinear Subspace Modeling for Prediction and Control of Molten Iron Quality Indices in Blast Furnace Ironmaking", IEEE Transaction on Control System Technology, 2017. | |
Heda Song, Ping Zhou, Hong Wang, Tianyou Chai, "Nonlinear Subspace Modeling of Multivariate Molten Iron Quality in Blast Furnace Ironmaking and Its Application", ACTA AUTOMATICA SINICA, 2016. |