Skip to content

Python code to replicate the results on HIGGS and SUSY benchmarks using pylearn2 and theano.

Notifications You must be signed in to change notification settings

cantel/higgs-susy

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

higgs-susy

This project contains python code to replicate the results in the following publication:

Baldi, P., P. Sadowski, and D. Whiteson. “Searching for Exotic Particles in High-energy Physics with Deep Learning.” Nature Communications 5 (July 2, 2014).

Warning: Pylearn2 is no longer being developed. For more active deep learning software frameworks, check out Keras, Tensorflow, etc.

Note: Due to an old bug in the Pylearn2 termination_criteria module, the deep models were trained for ~1000 epochs. The models here may terminate training after only ~200 epochs, in which case the termination criteria should be changed to train for the full 1000 epochs to get the same results in the paper.

Additional Requirements:

  1. The HIGGS and SUSY datasets available from the UCI ML Repository

http://archive.ics.uci.edu/ml/datasets/HIGGS

http://archive.ics.uci.edu/ml/datasets/SUSY

  1. Pylearn2 and Theano

http://deeplearning.net/software/theano/

http://deeplearning.net/software/pylearn2/

About

Python code to replicate the results on HIGGS and SUSY benchmarks using pylearn2 and theano.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%