9 papers
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…
Tournament Informed Adversarial Quality Diversity
Timothée Anne, Noah Syrkis, Meriem Elhosni +5
Quality diversity (QD) is a branch of evolutionary computation that seeks high-quality and behaviorally diverse solutions to a problem. While adversarial problems are common, class…
Adversarial Coevolutionary Illumination with Generational Adversarial MAP-Elites
Timothée Anne, Noah Syrkis, Meriem Elhosni +4
Quality-Diversity (QD) algorithms seek to discover diverse, high-performing solutions across a behavior space, in contrast to conventional optimization methods that target a single…
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…
Hypernetworks That Evolve Themselves
Joachim Winther Pedersen, Erwan Plantec, Eleni Nisioti +4
How can neural networks evolve themselves without relying on external optimizers? We propose Self-Referential Graph HyperNetworks, systems where the very machinery of variation and…