Learn Data Science by Doing Kaggle Competitions: Adversarial Attacks


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!

This time we will be the discussion the NIPS 2017 Adversarial competitions. There are three related competitions:

• Non-targeted Adversarial Attack (https://www.kaggle.com/c/nips-2017-non-targeted-adversarial-attack)

• Targeted Adversarial Attack (https://www.kaggle.com/c/nips-2017-targeted-adversarial-attack)

• Defense Against Adversarial Attack (https://www.kaggle.com/c/nips-2017-defense-against-adversarial-attack)

Our presenters will be Aleksey (https://www.meetup.com/LearnDataScience/members/46167562/) and Ross (https://www.meetup.com/LearnDataScience/members/60644062/), who participated in the competitions and did very well. Come to the meetup to find out just how well. :)

To get the most out of the meetup, please try to look at the competition 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

Thanks to VentureLabs (http://www.venturelabs.ca/) for the meeting space!