Continual Learning for Particle Accelerators
Unfortunately, I could not travel to the conference, thanks to Malachi Schram for presenting this spotlight Talk on our paper "Continual Learning for Particle Accelerators"
admin
•
December 6, 2025 12:00 AM — 12:00 AM
•
1 min read
Uncertainty based online ensemble on non-stationary data for fusion science
We present an uncertainty-aware online ensemble method for handling non-stationary data streams in fusion science applications. The approach dynamically weights multiple models …
rajput-k.
Continual learning for particle accelerators
This paper addresses the challenge of continual learning in particle accelerators, where machine learning models must adapt to changing data distributions and system configurations …
rajput-k.
Towards a Robust Adaptive Digital Twin for Fusion Applications
Talk Talk on developing robust adaptive digital twins with uncertainty awareness for fusion science applications.
admin
Differential and Explainable Reinforcement Learning for Multi-objective Optimization in Particle Accelerators
Invited Talk Explainable and Differential Reinforcement Learning for Multi-objective Optimization in Particle Accelerators
admin
Hydra: An AI-Based Framework for Interpretable and Portable Data Quality Monitoring
Hydra is an advanced framework designed for training and managing AI models for near real time data quality monitoring at Jefferson Lab. Deployed in all four experimental halls, …
britton-t.
Towards continual machine learning for particle accelerators
This paper presents results from ongoing efforts to develop continual learning methods for particle accelerators. We address the challenge of model adaptation to changing …
rajput-k.
Towards continual machine learning for your ever-changing accelerators
Invited Talk Continual/Lifelong machine learning for ever drifting particle accelerator data at IBIC 2025, University of Liverpool, UK.
admin
Geometric GNNs for Charged Particle Tracking at GlueX
Graph Neural Networks (GNN) applied to track charged particle tracking at GlueX experiment at Jefferson Lab. GNN shows better performance compared to traditional method while being …
mohammed-a.-h.
Toward an event-level analysis of hadron structure using differential programming
We introduce a differential sampling method called the local orthogonal inverse transform sampling (LOITS) algorithm. We validate its performance through a closure test, …
braga-k.
An Outlook Towards Deployable Continual Learning for Particle Accelerators
Particle accelerators rely on the precise synchronization of thousands of components, but data distribution drifts often limit the long-term deployment of machine learning …
rajput-k.
SAGIPS: a physics-inspired scalable asynchronous generative inverse-problem solver
A Scalable Asynchronous Generative Inverse Problem Solver (SAGIPS) on high-performance computing systems. We present a workflow that utilizes an asynchronous ring-allreduce …
lersch-d.
Hydra: computer vision for data quality monitoring
Hydra is a system that utilizes computer vision to perform near real time data quality monitoring. Since then, it has been deployed across all experimental halls at Jefferson Lab, …
britton-t.
Distance preserving machine learning for uncertainty aware accelerator capacitance predictions
This paper presents a distance-preserving machine learning approach for making uncertainty-aware predictions of accelerator capacitance. The method preserves geometric …
goldenberg-s.
Errant Beam Prognostics with Machine Leaning at SNS Accelerator
Invited Talk Talk on application of conditional machine learning models to predict anomalies before they occur at SNS accelerator.
admin
Composable Optimization and Control Toolkit for Scientific Applications
Invited Talk Long term software steward requires composable modular development and management.
admin
Machine Learning for Prognostics and Optimization of Particle Accelerators
Invited Talk Current progress on machine learning applications for particle accelerators and its scope for Fusion Science.
admin
AI4EIC Hackathon: PID with the ePIC dRICH
This paper presents results from the AI4EIC Hackathon, specifically focusing on particle identification (PID) with the ePIC dRICH detector. Machine learning techniques were applied …
fanelli-c.
Fault Prediction in Particle Accelerators
Guest Lecture Guest lecture within the graduate particle accelerators class at ODU department of physics.
admin
Robust errant beam prognostics with conditional modeling for particle accelerators
Conditional Models to handle data drifts due to changes in beam configuration changes at SNS accelerator.
rajput-k.
Machine Learning to Improve Accelerator Operation at SNS
Invited Talk Application of Machine Learning to improve accelerator operation, application of conditional models to predict anomalies at SNS accelerator.
admin
Model up-keep with Continual Learning for Particle Accelerators
Invited Tutorial Lecture on Model up-keep / Continual Learning for Particle Accelerators at MaLAPA 2024, Gyeongju, South Korea.
admin
Artificial Intelligence for the Electron Ion Collider (AI4EIC)
This is an opportune time for artificial intelligence (AI) to be included from the start at the upcoming Electron Ion Collider facility and in all phases that lead up to the …
allaire-c.
SOCT (Scientific Optimization Control Toolkit)
Scientific Optimization Control Toolkit (SOCT) is an open-source Python framework built on OpenAI Gymnasium for designing and deploying reinforcement learning agents for scientific …
•
1 min read
SMOCS (Coming Soon)
Scientific Monitoring, Optimization and Control System (SMOCS) is an end-to-end solution for ML deployment in large complex systems.
•
1 min read
L3Kit (Coming Soon)
Lifelong Learning Layer Toolkit (L3Kit) is a framework for modern continual learning evaluation and deployment.
•
1 min read
Uncertainty aware machine-learning-based surrogate models for particle accelerators: Study at the Fermilab Booster Accelerator Complex
Surrogate models based on machine learning are increasingly used to accelerate optimization and control of particle accelerators. This paper presents methods for quantifying …
schram-m.
Uncertainty Quantification for Rare Events in Scientific Applications
Uncertainty Quantification for Rare Events (Out-of-Distribution Detection) via Gaussian Process Approximation in Scientific Applications
admin
Anomaly Detection and Online Data Quality Monitoring
Online data quality monitoring with ML (Hydra) and Anomaly Detection on streaming data from physics and particle accelerator experiments.
admin
Hydra - Layer-wise Relevance Propagation
Potential applications of explainable ML techniques such as Layer-wise relevance propagation in Medical Sciences
admin