Choose timezone
Your profile timezone:
QUC Summer School on “A.I. in High Energy Physics,” Part II, Recent Development in AI
→
Asia/Seoul
Building #1, 1503 (KIAS)
Building #1, 1503
KIAS
, , , , ,
Description
This year's school will highlight emerging developments in artificial intelligence (AI) and machine learning. There will be active interaction with the lecturers, fostering discussions that may naturally develop into collaborative research projects. The school is intended for students and postdoctoral researchers seeking to deepen their understanding of the field and explore emerging research directions.
The registration fee is 100,000 KRW and should be paid in cash at on-site registration.
Lectures
- Jack Y. Araz (City St. George’s, University of London)
Artificial Intelligence for High-Energy Physics
This lecture series provides an introduction to artificial intelligence for high-energy physics. It covers supervised and unsupervised learning, generative models, simulation-based inference, and modern architectures for particle-physics data. Complementary lectures discuss symmetry-aware learning, uncertainty quantification, and the integration of theoretical knowledge into machine-learning methods.
- Sven Krippendorf (Cambridge U. DAMTP)
Agentic AI for Theoretical Physics: From Research Questions to Verifiable Results
This lecture series provides an introduction to agentic AI for theoretical physics. It covers coding agents, agentic research workflows, literature and tool use, and methods for verifying and reproducing AI-assisted results. Complementary lectures introduce theoretical foundations of neural networks, including Gaussian-process and neural-tangent-kernel limits. The accompanying hands-on tutorials explore research projects with agents.
- Michael Spannowsky (KIT, Karlsruhe)
Quantum Machine Learning for Fundamental Physics
This lecture series provides an introduction to quantum machine learning with applications to fundamental physics. It covers quantum data encoding, variational quantum circuits, quantum kernels, quantum neural networks, and hybrid quantum-classical learning methods.
Contact Juhye Park