DEPARTMENT OF ELECTRICAL AND COMPUTER ENGINEERING (NUS)
Author | Under the supervision of |
Michaël Dell'aiera (LAPP, LISTIC) | Thomas Vuillaume (LAPP) Alexandre Benoit (LISTIC) |
Presentation outline
Contextualisation
**[Cherenkov Telescope Array (CTA)](https://www.cta-observatory.org/)**
* Exploring the Universe at very high energies * γ-rays, powerful messenger to study the Universe * Next generation of ground-based observatories * Large-Sized Telescope-1 (LST-1) operational
**[GammaLearn](https://purl.org/gammalearn)**
* Collaboration between LAPP (CNRS) and LISTIC * Fosters innovative methods in AI for CTA * Evaluate the added value of deep learning * [Open-science](https://gitlab.in2p3.fr/gammalearn/gammalearn)
Fig. Principle of detection
Particle distribution
**Many particles create atmospheric showers**
GammaLearn workflow
Physical attribute reconstruction
**Real labelled data are intrinsically unobtainable**
→ Training relying on simulations (Particle shower + instrument response)
* Machine learning * Morphological prior hypothesis: Ellipsoidal integrated signal * Image cleaning
GammaLearn* Deep learning (CNN-based) * No prior hypothesis * No image cleaning
Simulations and real data discrepencies
**Simulations are approximations of the reality**
Simulations and real data discrepencies
Data adaptation
**Modify the simulations to fit the acquisitions**
Setup
Train |
Test |
Labelled | Labelled |
MC+P(λ) ratio=50%/50% |
MC+P(λ) ratio=50%/50% |
Results with data adaptation on simulations
Setup
Train |
Test |
Labelled | Labelled |
MC+P(λ) ratio=50%/50% |
Real data ratio=1γ for > 1000p |
Results with data adaptation on Crab (real data)
Multi-modality
**Modify the model to make it robust to noise**
Setup
Train |
Test |
Labelled | Labelled |
MC+P(λ(t)) ratio=50%/50% |
MC+P(λ) ratio=50%/50% |
Results with multi-modality on simulations
Setup
Train |
Test |
Labelled | Labelled |
MC+P(λ(t)) ratio=50%/50% |
Real data ratio=1γ for > 1000p |
Results with multi-modality on Crab (real data)
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 * 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)
Domain adaptation
**Modify the model to make it domain agnostic**
Multi-task balancing
**[Multi-task balancing](https://arxiv.org/abs/1707.08114) (MTB): Simulateneous optimization of multiple tasks**
* In opposition to single-task learning * Correlated tasks help each other to learn better * Conflicting gradients (amplitude and/or direction) * Baseline: * Equal Weighting (EW) * Selection and implementation: * [Uncertainty Weighting](https://arxiv.org/abs/1705.07115) (UW) * [GradNorm](https://arxiv.org/abs/1711.02257) (GN)
Challenging multi-task optimization
Setup
Train |
Test |
|
Source Labelled |
Target Unlabelled |
Unlabelled |
MC ratio=50%/50% |
MC+P(λ) ratio=50%/50% (No label shift) |
MC+P(λ) ratio=50%/50% |
Results with domain adaptation on simulations
Setup
Train |
Test |
|
Source Labelled |
Target Unlabelled |
Unlabelled |
MC ratio=50%/50% |
MC+P(λ) ratio=1γ for > 1000p (Label shift) |
MC+P(λ) ratio=50%/50% |
Results with domain adaptation on simulations
Conditional domain adaptation
Results with domain adaptation on simulations
Setup
Train |
Test |
|
Source Labelled |
Target Unlabelled |
Unlabelled |
MC+P(λ) ratio=50%/50% |
Real data ratio=1γ for > 1000p |
Real data ratio=1γ for > 1000p |
Results with domain adaptation on Crab (real data)
Masked Auto-Encoder (MAE)
MAE applied to LST
Event reconstruction example 1
Event reconstruction example 2
Event reconstruction example 3
Event reconstruction example 4
Event reconstruction example 5
Results on simulations
Conclusion & Perspectives
Acknowledgments