Recent advances in the Machine Learning Methods for the High-Energy Physics

In my talk, I briefly cover several problems that are characteristic for the High-Energy Physics. These problems cover broad variety of tasks from data taking to the final physics analysis. I will take a closer look into the triggering system, anomaly detection, and data storage optimization based on dataset popularity. The abundance of data coming from modern experiments also gave interesting application techniques to be developed. In the second part of my talk, I will provide a description and an overview of the code for the flatness boosting techniques and the reweighting using the Boosted Decision Trees.