sitongan / machine-learning-hats

Machine Learning HATS with CMS Open Data

CMS Machine Learning Hands-on Advanced Tutorial Session (HATS)

Introduction

This is a set of tutorials for the CMS Machine Learning Hands-on Advanced Tutorial Session (HATS). They are intended to show you how to build machine learning models in python (Keras/TensorFlow) and use them in your ROOT-based analyses. We will build event-level classifiers for differentiating VBF Higgs and standard model background 4 muon events and jet-level classifiers for differentiating boosted W boson jets from QCD jets.

Main notebooks in this tutorial

0. 0-setup-libraries.ipynb: setting up libraries using CMSSW
1. 1-datasets.ipynb: reading/writing datasets from ROOT files and HDF5 files
2. 2-plotting.ipynb: plotting with pyROOT and matplotlib
3. 3-dense.ipynb: building, training, and evaluating a fully connected (dense) neural network in Keras
4. 4-preprocessing.ipynb: preprocessing CMS open data to build jet-images
5. 5-conv2d.ipynb: building, training, and evaluating a 2D convolutional neural network in Keras

Setup

We will be using the Vanderbilt JupyterHub. Point your browser to:

https://jupyter.accre.vanderbilt.edu/

If this is the first time using this JupyterHub, you should see:

Click the "Sign in with CILogon" button. On the following page, select CERN as your identity provider and click the "Log On" button. Then, enteri your CERN credentials or use your CERN grid certificate to autheticate.

Now you should see the JupyterHub home directory. Click on "New" then "Terminal" in the top right to launch a new terminal.

To download the tutorials, type

git clone https://github.com/FNALLPC/machine-learning-hats

Now, in your directory tab, there should be a new directory called machine-learning-hats. All of the tutorials and exercises are in there.

Links

The indico page is: https://indico.cern.ch/event/726984/

The Mattermost for live support is: https://mattermost.web.cern.ch/cms-exp/channels/machine-learning-hats