Research Expertise and Interest
machine learning, trustworthy data science and AI, interdisciplinary research in biomedicine, neuroscience, and climate science.
Research Description
Bin Yu is the Class of 1936 Second Chair in the College of Letters and Science and a Chancellor's distinguished professor in the Department of Statistics, EECS and Center for Computational Biology. She is also a scientific advisor at the Simons Institute for Theory of Computing. Her current research has focused on the practice and theory of statistical machine learning, veridical (truthful) data science, and solving interdisciplinary data problems in neuroscience, genomics, precision medicine (e.g. in ER and cardiology), and climate science. The Yu group has developed interpretable machine learning algorithms such as next-generation tree-based methods (e.g. iterative random forests (iRF), fast and greedy sums of trees (FIGS), HS, and MDI+), stability-driven NMF, and deep learning interpretation methods including contextual decomposition (CD) and and adaptive wavelet distillation (AWD).
In the News
When Data Science Meets Medicine
UC Berkeley Joins NSF-Backed AI Institute for Cybersecurity
UC Berkeley to lead $10M NSF/Simons Foundation program to investigate theoretical underpinnings of deep learning
Getting the right equipment to the right people
Seeking Data Wisdom
Bin Yu’s statistical strategies work hand in hand with intense computation to penetrate storms of data.