Three principles of data science: predictability, stability, and computability
[Math. Dept.]
April 28, 2018 09:00-10:00
W303 School of Mathematics
SPEAKER
Bin Yu (University of California, Berkeley)
Abstract
In this talk, I'd like to discuss the intertwining importance and connections of three principles of data science in the title. They will be demonstrated in the context of two collaborative projects in neuroscience and genomics, respectively. The first project in neuroscience uses transfer learning to integrate fitted convolutional neural networks (CNNs) on ImageNet with regression methods to provide predictive and stable characterizations of neurons from the challenging primary visual cortex V4. The second project proposes iterative random forests (iRF) as a stabilized RF to seek predictable and stable high-order interactions between biomolecules for interpretation and to arrive at scientific recommendations for follow-up experiments.
SUPPORTED BY
School of Mathematics, Sichuan University
VIDEO
- Three principles of data science: predictability, stability, and computability
- 09:00 - 10:00, 2018-04-28 at W303 School of Mathematics
- Bin Yu (University of California, Berkeley)