IN2P3/IRFU Machine Learning workshop 2025

Session

Generative and Probabilistic Models

autoencoders

28 nov. 2025, 09:20

G. Iltis (LPC) and Seminar room maison d'hôtes (GANIL) (LPC Caen and GANIL)

Présidents de session

Generative and Probabilistic Models

• Sylvain Caillou (L2I Toulouse, CNRS/IN2P3, Université de Toulouse)

163. Probabilistic Inference of Galaxy Properties from Multi-Modal Latent Space Representations

Kirill Grishin (Astroparticle and Cosmology Lab., CNRS)

28/11/2025 09:20

Analysis : event classification, statistical analysis and inference, anomaly detection

Cosmological research in the era of deep, wide-area surveys such as Euclid and Rubin/LSST benefits greatly from combining datasets collected with different instruments. However, the large volume of data makes analysis increasingly challenging. To address this, we developed a package based on the Variational Autoencoder (VAE) architecture that enables compact representations of spectroscopic...

140. Shower shapes correction via normalising flows

Katerina Kazakova (CPPM, Aix-Marseille Université, CNRS/IN2P3 (FR))

28/11/2025 09:40

Analysis : event classification, statistical analysis and inference, anomaly detection

Mismodeling of calorimeter shower shape observables has been present since the beginning of the ATLAS detector due to a mismodelling in the Geant4 detector simulation. Shower shape variables are discriminating observables used in the identification of electrons and photons, and accurate modelling of their distributions is essential for precision measurements and searches in high-energy...

159. Dual-Decoder Convolutional Autoencoder for Unsupervised Anomaly Detection and Denoising in BPM Data

Charles Ndegwa (CentraleSupélec / LISN / CNRS, Paris-Saclay University, Gif-sur-Yvette, France)

28/11/2025 10:00

Analysis : event classification, statistical analysis and inference, anomaly detection

Turn-by-turn beam position monitor (BPM) data are vital for fast optics diagnostics in modern colliders, but they are often degraded by noise, spikes, and signal dropouts. We present ongoing work on a dual-decoder convolutional autoencoder that addresses these issues in an unsupervised setting. A shared encoder compresses BPM waveforms into a latent representation. Two decoders then serve...

167. Interdisciplinary Digital Twin Engine InterTwin for calorimeter simulation

Vera MAIBORODA (IJCLab, CNRS)

28/11/2025 10:20

Simulations and surrogate models : replacing an existing complex physical model

The interTwin project develops an open-source Digital Twin Engine to integrate application-specific Digital Twins (DTs) across scientific domains. Its framework for the development of DTs supports interoperability, performance, portability and accuracy. As part of this initiative, we implemented the CaloINN normalizing-flow model for calorimeter simulations within the interTwin framework....

171. Hybrid Autoencoder-Isolation Forest Approach for Time Series Anomaly Detection in C70XP Cyclotron Operation Data at ARRONAX

Fatima Basbous (Arronax)

28/11/2025 10:40

Analysis : event classification, statistical analysis and inference, anomaly detection

The Interest Public Group ARRONAX's C70XP cyclotron, used for radioisotope production for medical and research applications, relies on complex and costly systems that are prone to failures, leading to operational disruptions. In this context, research is being conducted to develop an active machine learning method for early anomaly detection to enhance system performance. One of the most...