BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Emergence\, Self-Organisation\, and the Future of Adaptive AI
DTSTART:20260408T130000Z
DTEND:20260408T140000Z
DTSTAMP:20260610T222900Z
UID:indico-event-2175@indico.lip.pt
CONTACT:pbras@lip.pt\;psilva@uc.pt
DESCRIPTION:Speakers: José Sousa (AI4 Continuous Learning Lab (AI4CL) Mul
 tidisciplinary Institute of Ageing (MIA) University of Coimbra)\n\nThe dom
 inant paradigm in Artificial Intelligence (AI) rests on a single premise: 
 that learning scales with data and computation. Large Language Models (LLM
 s) and Deep Learning (DL) architectures have normalised this assumption\, 
 yet they remain fundamentally brittle — unable to generalise beyond thei
 r training distribution\, incapable of continuous learning\, and dependent
  on human feedback to adapt. This talk proposes a different foundation.Dra
 wing on the physics of complex adaptive systems\, we present GALILEAN\, a 
 project developing a theory and architecture for AI continuous learning gr
 ounded in adaptive spiking neural networks (aSNNs). The central hypothesis
  is that tacit knowledge — experiential\, non-codified\, and resistant t
 o explicit representation — can emerge as a collective property of inter
 acting intelligent agents\, much as macroscopic order emerges from microsc
 opic interactions in statistical physics.We model this as an aSNN in which
  agents form probabilistic beliefs from raw data without training or valid
 ation pipelines\, share those beliefs through spike trains\, and self-orga
 nise from fully connected to scale-free network topologies driven by spike
 -timing-dependent plasticity. Evolutionary game theory (EGT) provides the 
 measurement language\, mapping agent interaction dynamics onto attractor l
 andscapes in phase space.The framework is empirically grounded in a longit
 udinal clinical dataset involving nine clinicians diagnosing allergy disea
 ses\, with further validation planned for age-related macular degeneration
  diagnosis. Open questions — on the conditions for emergence\, the role 
 of information coupling\, and the stability of knowledge attractors — ar
 e framed across physics\, network science\, cognitive sciences and informa
 tion theory.\nhttps://www.uc.pt/mia/research/ai-4-continuous-learning/\n\n
 https://indico.lip.pt/event/2175/
LOCATION:Sala de Conferências (Departamento de Física FCTUC)
URL:https://indico.lip.pt/event/2175/
END:VEVENT
END:VCALENDAR