...
The division into categories is multidimensional
- Dimension 1: per goal (classification, regression, clustering, technological ...)
- Dimension 2: per Machine Learning technology algorithms (CNN, Auto encoders, LSTM, GraphNet, ...)
- Dimension 13: per scientific field (High Energy Physics, Gravitational Waves, Medical Physics, ...)
- Dimension 34: per type of used tool
and is implemented via Confluence labels.
Table of Use cases
Name and Link | Goal | ML |
---|
Algorithms | Scientific Field | ML Tools | Comments | ||
---|---|---|---|---|---|
Btagging in CMS (templated version) | Classification | CNN, LSTM | High Energy Physics | Keras + Tensorflow | Realistic application |
LHCb Masterclass, with Keras | Density estimation and classification |
MLP | High Energy Physics | ROOT + Keras + TF | Introductory tutorial | ||
MNIST in a C header | Classification | MLP | Keras | Free-styling tutorial | |
Technological | CNN, RNN, GNN | High Energy Physics | PyTorch | Package use examples | |
INFERNO: Inference-Aware Neural Optimisation | Classification | NN | High Energy Physics | Keras + Tensorflow | Technique application example |
An introduction to classification with CMS data | Classification | Fisher, BDT, MLP | High Energy Physics | Scikit-learn, TF2 | Tutorials for Master Students |
Virgo Autoencoder tutorial | Data Compression | Autoencoder | General Relativity | Python Keras | Tutorial for student |
Distributed training of neural networks with Apache Spark | Technological | DNN | High Energy Physics | Spark + BigDL | Tutorial |
FTS log analysis with NLP | Self-supervised, clustering | NLP | High Energy Physics, Computing | Word2Vec + Rake + sklearn | Tutorial |
Image Inpainting tutorial: how to digitally restore damaged images | Inpainting | CNN U-Net | Applied Physics | Keras + Sci-kit image, PIL, OpenCV, matplotlib | Tutorial |
ANNs, RF | High Energy Physics | Keras , TensorFlow, Scikit-learn | Tutorial | ||
CNN | Medical Physics | Keras, Tensorflow | Tutorial | ||
ML/RL | High Energy Physics, Computing, Cache | Keras, Tensorflow, sklearn | Demo, playground | ||
pNN | High Energy Physics | Keras + TensorFlow 2 | Tutorial | ||
New Physics Learning Machine | Density Estimation | NN | High Energy Physics | Keras, Tensorflow | package + tutorial |
MLaaS4HEP for the Higgs boson ML challenge | Technological | DT, MLP | High Energy Physics | XGBoost, Keras + TensorFlow 2, PyTorch | Tutorial |
Object counting with c-ResUnet | Supervised learning, Semantic Segmentation | CNN, ResUnet | Computer Vision | PyTorch, fastai | Real application, Tutorial |
Fast classifier-based goodness of fit test for online data quality monitoring | Density estimation | Logistic Regression, Kernel Methods | High Energy Physics | Pytorch, Falkon library | Tutorial + Realistic application |
How to insert a new use case
...
Once you finish with the creation of the page don't forget to edit the page "33161472Machine Learning Knowledge Base" (this same page!) and add the use case in the "Table of Use cases".
...