9th International Conference on New Frontiers in Physics (ICNFP 2020)

Session

Mini-workshop on Machine Learning for Particle Physics

5 Sept 2020, 16:30

197. Outlier detection in heavy-ion collisions with unsupervised learning

Punnatat Thaprasop (SUT)

05/09/2020, 16:30

Talk

High energy nuclear collision experiments produce large amounts of data which are often challenging to handle. We present machine learning algorithms using unsupervised learning to find so-called outlier events which might occur e.g. due to detector malfunction or imperfect centrality determination. Their detection can be crucial for the correct determination of sensitive observables. We...

88. New approaches to the problem of unfolding

Dr Pietro Vischia (Universite Catholique de Louvain (UCL) (BE))

05/09/2020, 16:55

Talk

Matrix inversion problems are often encountered in experimental physics, and in particular in high-energy particle physics, under the name of unfolding. The true spectrum of a physical quantity is deformed by the presence of a detector, resulting in an observed spectrum. If we discretize both the true and observed spectra into histograms, we can model the detector response via a matrix....

211. Machine Learning (CMS)

Samuel May (Univ. of California San Diego (US))

05/09/2020, 17:20

Talk

Advanced machine learning methods are increasingly used in CMS physics analyses to maximize the sensitivity of a wide range of measurements. The landscape is diverse in terms of both methods and applications. Deep learning methods, from recurrent LSTM architectures for classification tasks to deep autoencoders for data quality monitoring, have greatly improved the physics results delivered...

58. Cluster analysis of Very Long Period events at Stromboli Volcano recorded by the Italian National Institute of Geophysics and Volcanology INGV

Lukas Layer (Universita e INFN, Padova (IT))

01/10/2020, 16:35

Talk

The Stromboli Volcano erupted on July 3, 2019 and August 28, 2019 after a period of modest activity. The paroxysm on July 3rd was not predicted by the monitored parameters that characterize the activity of the volcano. This motivates the study of alternative seismic parameters in the eruption period in order to identify parameters that have potential to predict paroxysms in the future using...