From the 1 of 7 linked papers with an AI index.
7 papers
Learning Developmental Scaffoldings to Guide Self-Organisation
Milton L. Montero, Elias Najarro, Jakob Schauser +1
The paper introduces a model that simultaneously learns initial pre‑patterns and self‑organisation rules using a Neural Cellular Automaton and a coordinate‑based pattern generator,…
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…
When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?
Eleni Nisioti, Joachim Winther Pedersen, Erwan Plantec +2
The ability to continuously and efficiently transfer skills across tasks is a hallmark of biological intelligence and a long-standing goal in artificial systems. Reinforcement lear…
Meta-Learning an Evolvable Developmental Encoding
Milton L. Montero, Erwan Plantec, Eleni Nisioti +2
Representations for black-box optimisation methods (such as evolutionary algorithms) are traditionally constructed using a delicate manual process. This is in contrast to the repre…
Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning
Erwan Plantec, Joachin W. Pedersen, Milton L. Montero +2
Biological neural networks are characterized by their high degree of plasticity, a core property that enables the remarkable adaptability of natural organisms. Importantly, this ab…
Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents
Joachim Winther Pedersen, Erwan Plantec, Eleni Nisioti +2
Artificial neural networks used for reinforcement learning are structurally rigid, meaning that each optimized parameter of the network is tied to its specific placement in the net…