The Large Hadron Collider (LHC) is the largest data generation machine for the time being. It doesn’t produce the big data, the data is gigantic. Just one of the four experiments generates thousands gigabytes per second. The intensity of data flow is only going to be increased over the time. So the data processing techniques have to be quite sophisticated and unique. In this course we’ll introduce students into the main concepts of the Physics behind those data flow so the main puzzles of the Universe Physicists are seeking answers for will be much more transparent. Of course we will scrutinize the major stages of the data processing pipelines, and focus on the role of the Machine Learning techniques for such tasks as track pattern recognition, particle identification, online real-time processing (triggers) and search for very rare decays. The assignments of this course will give you opportunity to apply your skills in the search for the New Physics using advanced data analysis techniques. Upon the completion of the course you will understand both the principles of the Experimental Physics and Machine Learning much better.
Do you have technical problems? Write to us: firstname.lastname@example.org
Introduction into particle physics for data scientists
-This module starts with a mild introduction into particle physics, and it explains basic notions, so you will understand the structure and the principal terms that physicists are using to describe the forces and particles that comprise the fundamental level of our universe. Also, we'll describe main stages of data collection and analysis that happens at LHC experiment. Each step is associated with specific machine learning challenges and some of which we are going to cover later. The final part of the module describes a very high-level example of data analysis that shows how simple data analysis techniques can be used for discovery of an elementary particle.
-This module is about detectors in high energy physics. It describes several detector designs, different detector systems, how they work and what particle parameters they measure. Several cases in high energy physics where machine learning can be successfully applied are demonstrated.
Search for New Physics in Rare Decays
-In this module, we explain how new physics search can be mediated through a search for rare processes. We describe the main steps physicists have to follow to find rare decay. At first search for such phenomena may look like a perfect task for machine learning algorithms. However, there are several constraints that one have to keep in mind during training and application of a classifier.
Search for Dark Matter Hints with Machine Learning at new CERN experiment
-We start this module with explanation what Dark Matter phenomenon is about and what are the general strategies for Dark Matter search. Then we boil down the topic towards one of the CERN proposed experiments - SHiP. Given the design of the experiment, we consider the signatures that Dark Matter particles may produce. Of course, Machine Learning algorithms can be applied to discriminate such signatures from the background. We'll see how clustering algorithms can improve the signal visibility even further.
-This module covers several cases of detector design optimization in high energy physics experiments using Bayesian optimization with Gaussian processes.
Andrei Ustyuzhanin and Mikhail Hushchyn