Alex thinks dropout is cool. He's still not quite sure what batch normalization is. Regarding ImageNet competition, Apurva, along with offering tips to staying motivated to learning  says that instead of creating "new" models, people are only doing ensembling now to get a marginal edge over everyone else. Edderic announces revamping his PC workstation for deep learning (bye-bye Amazon!)

Episode 007 - Lesson 3 - Part 2 (Practical Deep Learning for Coders)

Startup Data Science is the podcast where you learn startup-ready data science with programming basics. We discuss how to bootstrap data science techniques and understand their underlying mechanics by discussing open-source learning materials. Startup Data Science helps forward-thinking entrepreneurs, novice programmers, and seasoned software engineers to use Data Science to make a bigger impact.