BEGIN:VCALENDAR VERSION:2.0 PRODID:-//linuxsoftware.nz//NONSGML Joyous v1.4//EN BEGIN:VEVENT SUMMARY:The impact of Artificial Intelligence on precision Higgs Boson phy sics DTSTART:20250326T160000Z DTEND:20250326T180000Z DTSTAMP:20260810T122356Z UID:0045ba8d-c640-4239-9727-89d8b306a801 SEQUENCE:2 CREATED:20250318T145026Z DESCRIPTION:Particle physics has a long history of developing sophisticate d simulators\, from modeling proton collisions to creating virtual detecto rs. Now\, we'\;re integrating Artificial Intelligence through "\;N eural Simulation Based Inference\,"\; which helps analyze complex phen omena that cannot be to computed analytically from first principles. This approach is highlighted by recent work from the ATLAS experiment at the L arge Hadron Collider at CERN\, which has provided new insights into quantu m interference in a rare Higgs boson decay. We also touch on how biases (& quot\;known unknowns"\;) are modeled\, as showcased in the recent Fair Universe HiggsML uncertainty challenge at NeurIPS 2024. Separately\, adv ances in AI generative models\, which allow to generate fake images\, can be harnessed to emulate particle physics simulators\, albeit with specific challenges which will be presented. LAST-MODIFIED:20250318T145052Z LOCATION:Anfiteatro PA1 (Piso -1 do Pavilhão de Matemática) do IST URL:http://df.vps.tecnico.ulisboa.pt/pt/eventos/the-impact-of-artificial-i ntelligence-on-precision-higgs-boson-physics/ X-ALT-DESC;FMTTYPE=text/html:

Particle physics ha s a long history of developing sophisticated simulators\, from modeling pr oton collisions to creating virtual detectors. Now\, we'\;re integrati ng Artificial Intelligence through "\;Neural Simulation Based Inferenc e\,"\; which helps analyze complex phenomena that cannot be to compute d analytically from first principles.

 This approach is highligh ted by recent work from the ATLAS experiment at the Large Hadron Collider at CERN\, which has provided new insights into quantum interference in a r are Higgs boson decay. We also touch on how biases ("\;known unknowns& quot\;) are modeled\, as showcased in the recent Fair Universe HiggsML unc ertainty challenge at NeurIPS 2024.

 Separately\, advances in AI generative models\, which allow to generate fake images\, can be harnesse d to emulate particle physics simulators\, albeit with specific challenges which will be presented.

END:VEVENT END:VCALENDAR