Machine Learning in High Energy Physics: The power of Normalizing Flows.

Since a few years, Machine Learning (ML) has been making strong strides towards revolutionizing the field of High Energy Physics (HEP). ML applications are being actively explored by experimenters and theorists for a wide variety of tasks. Examples include, acceleration of the simulation of fundamental processes, the reconstruction of unfolding of events, developing data-driven searches for new physics, learning experimental likelihoods, establishing novel triggering strategies, and many more. After giving an overview of the rapidly growing field of ML in HEP, we will focus on a particularly interesting method: the so-called Normalizing Flows. These are highly expressive generative networks with explicit density estimation. We will demonstrate their varied applicability and use it to showcase the importance of thoroughly testing ML methods to ensure their systematic usage.

https://cuaieed-unam.zoom.us/j/87555674435?pwd=eEZMWE1oSXdva0djVkpsVEdiV2ZaUT09

Meeting ID: 875 5567 4435
Passcode: 609509