Twitter

What are your favorite add-ons to GitHub?

Apps, bots, browser extensions — what tools make GitHub better for you?

How to solve 90% of #NLP problems: a step-by-step guide #KDN https://t.co/CdXbIDk9te

New YouTube video: learn how to create ensembles for @kaggle with my #Python code examples. https://t.co/pGgDafiMxS

Interesting AutoML research in last year:
BOHB: robust and efficient hyperparasite optimization at scale
https://t.co/QKSMg11jKd
OBOE: Collaborative Filtering for AutoML Initialization https://t.co/aiKF2VbSKP
ENAS
https://t.co/rb2H5rAVkx
@ledell keynote #DSCO19

Tapson's Rules of Machine Learning:
4. Time spent on data cleaning is an order of magnitude more productive than time spent on hyperparameter tuning.

(Extreme example: achieved a Top 10 result in Kaggle using linear regression, as the only team that cleaned 50/60Hz noise first.)

Feeling like training a deep RL navigation agent on Street View? We have #streetlearn for you! Code at https://t.co/vJ6oTYw1dA, curated dataset for Manhattan and Pittsburgh at https://t.co/GSUNnrXjoV! With @bhandras Keith Anderson, Denis Teplyashin, @RaiaHadsell et al @DeepMindAI

We’re releasing a Neural MMO — a massively multiagent game environment that supports numerous populations of agents: https://t.co/nED4DfUeEo
- Code: https://t.co/npVlxI0sTa
- 3D Client: https://t.co/k7t0gPXo2I

Load More...

Tzeny