We meet every two weeks to learn more about data science by discussing Kaggle competitions (https://www.kaggle.com). If you want to get better at data wrangling, feature engineering, model selection or just want to have fun solving non-trivial data science problems, this is the right group to join!
We're doing something a little different this time. Instead of talking about a competition, we're going to go through an excellent recent blog post by Andrej Karpathy, "A Recipe for Training Neural Networks" (http://karpathy.github.io/2019/04/25/recipe/). We'll be led through the discussion by Dan. (Thanks, Dan!)
We expect this will be a very interactive discussion that will be of interest to beginners and experienced network trainers alike.
To get the most out of the meetup, please try to look at the blog post beforehand. It's OK if you don't understand it all. The meetup is for questions and discussion.
At the end of the meeting we will discuss which competitions we want to look at for future meetups. Bring your suggestions!
6:00 Doors are open, feel free to mingle
6:30 Presentation and discussion begins
~7:45 Pick the next competition, then off to a nearby restaurant for food, drinks, and breakout discussions
The meetup will be live streamed here:
A list of past meetups and the slides and videos for them is here:
Discussions about this meetup also happen on Slack. To join, go here: http://vantech.herokuapp.com/. Once you're in, join the #kaggle-competitions channel.
Thanks to VentureLabs (http://www.venturelabs.ca/) for the meeting space!