GammaLearn update status
Author | Under the supervision of |
Michaël Dell'aiera (LAPP, LISTIC) | Thomas Vuillaume (LAPP) Alexandre Benoit (LISTIC) |
Contextualisation
**[GammaLearn](https://purl.org/gammalearn)** * Fosters innovative methods in AI for CTA * Evaluate the added value of deep learning
**[Main results (Published)](https://arxiv.org/abs/2108.04130)** * Outperforms Hillas+RF on MC and on real data in controlled environment * But performances on real data could be improved → Domain adaptation
Sensitivity of γ-PhysNet to NSB
Simulations and real data discrepencies
**Simulations are approximations of the reality**
* Poisson approximation * Independent pixels
* Some pixels are correlated
Data adaptation (or data tuning)
**Modify the simulations to fit the acquisitions**
Train |
Test |
Labelled | Labelled |
MC+P(λ) ratio=50%/50% |
MC+P(λ) ratio=50%/50% |
Results with data adaptation on Crab (real data)
γ-PhysNet-CBN (Conditional Batch Norm)
**Modify the model to make it robust to noise**
Setup
Train |
Test |
Labelled | Labelled |
MC+P(λ~Uniform()) ratio=50%/50% |
MC+P(λ) ratio=50%/50% |
Results with multi-modality on simulations
Results with multi-modality on Crab (real data)
Multi-modality
Domain adaptation
**[Domain adaptation](https://arxiv.org/abs/2009.00155): Set of algorithms and techniques to reduce domain discrepancies**
* Take into account unknown differences between the source (labelled, simulations) and target (unlabelled, real data) domains * Somehow include unlabelled real data in the training (→ label shift) * Selection, implementation and validation of [DANN](https://arxiv.org/abs/1505.07818) (focus of this talk), [DeepJDOT](https://arxiv.org/abs/1803.10081), [DeepCORAL](https://arxiv.org/abs/1607.01719)
Comparative study and validation
* Traditional deep learning dataset (digits) * Most of the difficulty resides in the optimization of the model (conflicting gradients) * Automatic determination of the loss coefficients * Gradient weighting strategy * Best performance using DANN paired with [Uncertainy Weighting](https://arxiv.org/abs/1705.07115) → **Paper #1**: Method-oriented with results on MC (will be send soon for your review)
γ-PhysNet-DANN (Domain Adversarial Neural Network)
**Modify the model to make it domain agnostic**
Application of γ-PhysNet-DANN to simulations
Conditional domain adaptation
Setup
Train |
Test |
|
Source Labelled |
Target Unlabelled |
Unlabelled |
MC ratio=50%/50% |
MC+P(λ) ratio~0.1%/99.9% (Label shift) |
MC+P(λ) ratio=50%/50% |
Results with domain adaptation on simulations
Results with domain adaptation on Crab (real data)
Conclusion & Perspectives
Acknowledgments