15 papers
Discovering Adaptive Transmission Programs for Collective Innovation
Cédric Colas, Jérémy Perez, Eleni Nisioti +4
Human collective intelligence depends on transmission processes: who shares what with whom, how, and when. While these processes emerge from individual cognition, they can also be…
Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise
John Myron Uy
Active learning can reduce labeling cost by selecting informative examples, but the most uncertain examples may also be the hardest to label correctly. This study tests whether unc…
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
Elias Najarro, Ane Espeseth, Eleni Nisioti +2
Complexity and interpretability rarely coincide: systems rich enough for complex behaviours to emerge are usually too opaque to question, while transparent ones are too simple for…
Dimensionality Controls When Modularity Helps in Continual Learning
Kathrin Korte, Christian Medeiros Adriano, Joachim Winther Pedersen +2
Compositional learning systems must balance plasticity, the ability to acquire new knowledge, with stability, the preservation of previously learned components, especially when tas…
Self-Organising Digital Circuits
Marcello Barylli, Gabriel Béna, Gabriel Béna +3
Fault tolerance in classical computing has traditionally relied on static strategies like hardware redundancy and error-correcting codes. Biological systems, in contrast, exhibit a…
When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry
Kathrin Korte, Joachim Winter Pedersen, Eleni Nisioti +1
To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stabi…