This section of the ML-INFN Confluence Space contains the Knowledge Base of fully implemented use cases. This has been created in order to provide new users getting close to Machine learning with concrete examples, with step by step guides for reproducibility.
The division into categories is multidimensional
- Dimension 2: per Machine Learning technology (CNN, Auto encoders, LSTM, GraphNet, ...)
- Dimension 1: per scientific field (High Energy Physics, Gravitational Waves, Medical Physics, ...)
- Dimension 3: per type of used tool
and is implemented via Confluence labels.
Table of Use cases
| Name and Link | ML Technologies | Scientific Field | ML Tools | Comments |
|---|---|---|---|---|
| Btagging in CMS (templated version) | CNN, LSTM | High Energy Physics | Keras + Tensorflow | Realistic application |
| LHCb Masterclass, with Keras | DE, MLP | High Energy Physics | ROOT + Keras + TF | Introductory tutorial |
| MNIST in a C header | MLP | Keras | Free-styling tutorial | |
| CNN, RNN, GNN | High Energy Physics | PyTorch | Package use examples | |
| INFERNO: Inference-Aware Neural Optimisation | NN | High Energy Physics | Keras + Tensorflow | Technique application example |
| An introduction to classification with CMS data | Fisher, BDT, MLP | High Energy Physics | Scikit-learn, TF2 | Tutorials for Master Students |
| autoencoder with gravitational data | Autoencoder | General Relativity | Python Keras | Tutorial for student |
| Distributed training of neural networks with Apache Spark | DNN | High Energy Physics | Spark + BigDL | Tutorial |
How to insert a new use case
- Open the page _Template KB Entry
- On the top right of the page, click on the 3 dots "..."
- Select "Copy"
- Make sure you select "Space → ML-INFN" and "Parent Page → Machine Learning Knowledge Page" (they should be already selected)
- A page with Title "Copy of _Template KB Entry" should open in the browser. Rename it with a proper name and click "Publish" on the lower right.
- You should see the page in view mode. Click on "Edit" on the top right to implement the use case following the template. Remember to "Publish" it.
- Edit the page "Machine Learning Knowledge Base" (this same page!) and add the use case in the "Table of Use cases".