Skip to content
master
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 

README.md

Parameterized-DNN

This code is used to do parameterized deep neural network for new particle search in the field of Particle Physics. General info, please refer to the paper: https://arxiv.org/pdf/1601.07913.pdf

The codes are under developed.

Structure:

  • make_array.ipynb: convert tree into numpy array, and save those array to h5 formart
  • work_all.ipynb: apply training, testing, and examination
  • write2tree.ipynb: write the DNN output results back to trees for further studies

If you are runing the code in your local PC, please install Keras[https://keras.io/] and its relevant tools firstly.

To use the notebooks, please install Jupyter. If without Jupyter, you can extract each code in notebook into separate python scripts.

About

A parameterized DNN based on the paper: https://arxiv.org/pdf/1601.07913.pdf for new particle search with unknown mass. The codes are currently used in low mass Z prime search analysis.

Resources

Releases

No releases published

Packages

No packages published
You can’t perform that action at this time.