PyData Amsterdam 2016
Optimizing hyper-parameters is a common yet time-consuming task for machine learning practitioners. Previous studies have shown that, when compared to traditional strategies like manual search and grid search, random search can achieve equal performance in a computationally efficient manner. In this talk I will demonstrate the random search feature in H2O with machine learning examples based on publicly available datasets.
Slides available here: http://www.slideshare.net/JofaiChow/20160312h2orandomgridsearch Other materials available here: https://github.com/h2oai/h2o-meetups/tree/master/2016_03_12_PyData_Amsterdam