https://github.com/mbarbetti/calotron

:package: Transformer-based models to flash-simulate the LHCb ECAL detector
https://github.com/mbarbetti/calotron

calorimeter deep-learning flash-simulation keras lhcb-experiment lhcb-lamarr machine-learning tensorflow transformer ultrafast-simulation

Last synced: 2 months ago
JSON representation

:package: Transformer-based models to flash-simulate the LHCb ECAL detector

• Host: GitHub
• URL: https://github.com/mbarbetti/calotron
• Owner: mbarbetti
• License: gpl-3.0
• Created: 2022-11-24T10:49:17.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-02T17:40:45.000Z (6 months ago)
• Last Synced: 2024-10-09T12:32:44.377Z (3 months ago)
• Topics: calorimeter, deep-learning, flash-simulation, keras, lhcb-experiment, lhcb-lamarr, machine-learning, tensorflow, transformer, ultrafast-simulation
• Language: Python
• Homepage:
• Size: 2.49 MB
• Stars: 0
• Watchers: 2
• Forks: 1
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  





  Transformer-based models to flash-simulate the LHCb ECAL detector





  

  

  

  





  

  





  

  



### Transformers

|         Models        | Implementation | Generative ability* | Test | Design inspired by |

|:---------------------:|:--------------:|:-------------------:|:----:|:------------------:|

|     `Transformer`     |       ✅       |          ❌          |  ✅  | [1](https://arxiv.org/abs/1706.03762), [4](https://arxiv.org/abs/2004.08249) |

| `OptionalTransformer` |       ✅       |          ❌          |  ✅  | [1](https://arxiv.org/abs/1706.03762), [4](https://arxiv.org/abs/2004.08249) |

|  `MaskedTransformer`  |       🛠️       |          ❌          |  ❌  | |

|    `GigaGenerator`    |       ✅       |          ✅          |  ✅  | [5](https://arxiv.org/abs/2303.05511), [6](https://arxiv.org/abs/2107.04589) |

*TBA

### Discriminators

|          Models         |  Algorithm  | Implementation | Test | Design inspired by |

|:-----------------------:|:-----------:|:--------------:|:----:|:------------------:|

|     `Discriminator`     |   DeepSets  |       ✅       |  ✅  | [2](https://cds.cern.ch/record/2721094), [3](https://arxiv.org/abs/1703.06114) |

| `PairwiseDiscriminator` |   DeepSets  |       ✅       |  ✅  | [2](https://cds.cern.ch/record/2721094), [3](https://arxiv.org/abs/1703.06114) |

|    `GNNDiscriminator`   |     GNN     |       🛠️       |  ❌  | |

|   `GigaDiscriminator`   | Transformer |       ✅       |  ✅  | [5](https://arxiv.org/abs/2303.05511), [6](https://arxiv.org/abs/2107.04589), [7](https://arxiv.org/abs/2006.04710) |

### References

1. A. Vaswani _et al._, "Attention Is All You Need", [arXiv:1706.03762](https://arxiv.org/abs/1706.03762)

2. N.M. Hartman, M. Kagan and R. Teixeira De Lima, "Deep Sets for Flavor Tagging on the ATLAS Experiment", [ATL-PHYS-PROC-2020-043](https://cds.cern.ch/record/2721094)

3. M. Zaheer _et al._, "Deep Sets", [arXiv:1703.06114](https://arxiv.org/abs/1703.06114)

4. L. Liu _et al._, "Understanding the Difficulty of Training Transformers", [arXiv:2004.08249](https://arxiv.org/abs/2004.08249)

5. M. Kang _et al._, "Scaling up GANs for Text-to-Image Synthesis", [arXiv:2303.05511](https://arxiv.org/abs/2303.05511)

6. K. Lee _et al._, "ViTGAN: Training GANs with Vision Transformers", [arXiv:2107.04589](https://arxiv.org/abs/2107.04589)

7. H. Kim, G. Papamakarios and A. Mnih, "The Lipschitz Constant of Self-Attention", [arXiv:2006.04710](https://arxiv.org/abs/2006.04710)

### Credits

Transformer implementation freely inspired by the TensorFlow tutorial [Neural machine translation with a Transformer and Keras](https://www.tensorflow.org/text/tutorials/transformer) and the Keras tutorial [Image classification with Vision Transformer](https://keras.io/examples/vision/image_classification_with_vision_transformer).