Skip to content

My MPhys project exploring extensions to the Standard Model of particle physics.

Notifications You must be signed in to change notification settings

benvlasto/MPhys-Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

82 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MPhys-Project

My MPhys project exploring extensions to the Standard Model of particle physics. This project involves deep learning with large datasets from the LHC.

Headline result so far: my CLs predicting model can correctly remove 45% of invalid models whilst removing only 1% of valid models. This translates to saving more than a month of processing by the LHC computing cluster out of a year total, for the recent EWKino scan.

Targets

  • Create model that predicts DM relic density better than random sampling of target range
  • Reduce MAE to below 25% of mean absolute target error
  • Create plot of MAE in bins of true relic density
  • Plot upper cutoff of relic density against number of valid but excluded pMSSM models
  • Apply EWKino model to Bino-DM and evaluate performance
  • Apply same relic density cutoff technique to CLs
  • Characterise those models which my CLs predictor incorrectly rejects
  • Recreate plots from pMSSM paper with predicted CLs

About

My MPhys project exploring extensions to the Standard Model of particle physics.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published