Deep Learning, Dark Knowledge, and Dark Matter
نویسندگان
چکیده
Particle colliders are the primary experimental instruments of high-energy physics. By creating conditions that have not occurred naturally since the Big Bang, collider experiments aim to probe the most fundamental properties of matter and the universe. These costly experiments generate very large amounts of noisy data, creating important challenges and opportunities for machine learning. In this work we use deep learning to greatly improve the statistical power on three benchmark problems involving: (1) Higgs bosons; (2) supersymmetric particles; and (3) Higgs boson decay modes. This approach increases the expected discovery significance over traditional shallow methods, by 50%, 2%, and 11% respectively. In addition, we explore the use of model compression to transfer information (dark knowledge) from deep networks to shallow networks.
منابع مشابه
Singlet scalar dark matter in noncommutative space
In this paper, we examine the singlet scalar dark matter annihilation to becoming the Standard Model particles in the non-commutative space. In the recent decades, many candidates of dark matter have been offered, but our information about the nature of dark matter is still limited. There are such particle candidates as scalar matetr, fermion, boson, gauge boson, etc.; however, they have nei...
متن کاملFormation of Large Structures in the Acceleration Universe with a Hybrid Expansion Law
In the current paper, we have studied the effect of dark energy on for-mation where dark energy exists in the background. For this purpose, we used both WMAP9 and Planck data to study how the radius changes with redshift in these mod-els. We used different data sets to fix the cosmological parameters to obtain a solution for a spherical region under collapse. The mechanism of structure formation f...
متن کاملFirst Results from the Cryogenic Dark Matter Search Experiment at the Deep Site
First Results from the Cryogenic Dark Matter Search Experiment at the Deep Site
متن کاملقیدهای تک Z روی مدل ماده تاریک فرمیونی با واسطه شبه اسکالر در LHC
In this research we study the Mono-Z signature along with dark matter production at the LHC in a renormalizable dark matter model. We look at processes with L+L-+MET in the final state. We simulate signal and background events at central mass energy 14 TeV We then evaluate the LHC sensitivities for some points in the model parameter space for two integrated luminosities L=100 fb-1 and L=1 ab-1 ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014