Colloquium

A Deep Learning Perspective of Recursive Partitioning Based Methods

  • Speaker: Heping Zhang (Yale University)

  • Time: Jun 22, 2018, 16:30-18:00

  • Location: Conference Room 415, Wisdom Valley 3#


4:30pm ~ 5:00pm: Yale University Biostatistics Information Session

5:00pm ~ 6:00pm: Colloquium


Abstract

Unlike any other method, deep learning has come as a forceful wave that knocked many of us to the sand, regardless of which direction we stood before. In this talk, I will begin with a brief introduction of the main steps of deep learning algorithm, and then use it to reflect on some of the statistical methods that I have developed over the past two decades, specifically classification trees for multiple binary responses (CTMBR) and multivariate adaptive splines for longitudinal data analysis (MASAL).  I will discuss the pros and cons of these methods, and offer my own perspective in our missed opportunities as well as new challenges and opportunities.