Yu Tian
 |
About me
I have received a Phd degree from Peking University 2010. Since 2019, I began to work as a machine learing engineer. Now I'm doing my postdoc in Aalto University Department of Computer Science. I've experienced in applying deep learning technologies for image analysis and natural language processing. Familiar with RNN, CNN, Pytorch, Tensorflow. Experience in medical research team focusing on health care data analysis applying common machine learning models.
Education & Career History
Researcher focusing on machine learning on graphs in Aalto University, 2021-
Researcher focusing on human genetic data analysis and disease prediction by applying machine learning models in Peking University, 2010-2019
Phd, MD, Medicine, Peking University, 2000-2010
Publications:A novel multi-locus genetic risk score identifies patients with higher risk of generalized aggressive periodontitis. Li W, Wang X, Tian Y, Xu L, Zhang L, Shi D, Feng X, Meng H. J Periodontol. 2019
GC Gene Polymorphisms and Vitamin D-Binding Protein Levels Are Related to the Risk of Generalized Aggressive Periodontitis. Song W, Wang X, Tian Y, Zhang X, Lu R, Meng H. Int J Endocrinol. 2016
Genetic study of families affected with aggressive periodontitis. Meng H, Ren X, Tian Y, Feng X, Xu L, Zhang L, Lu R, Shi D, Chen Z. Perodontol 2000.2011
Main Research Direction: Networked Lasso
Networked data are being generated from many applications including Internet of Things (IoT), social networking, and crowd-sourcing. Machine learning from these data distributed across multiple nodes,
without exchanging raw data or sending raw data to a centralized place has become a rapidly developing field, but also facing new challenges.
Networked lasso is a novel algorithm for unsupervised and semi-supervised learning from large collections of local datasets. This algorithm capitalizes on an intrinsic network structure that relates the local datasets via an undirected “empirical” graph.