1.4k citations
- Centre National de la Recherche ScientifiqueFR62 papers
- European Organization for Nuclear ResearchCH38 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali del Gran SassoIT24 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT22 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di TriesteIT21 papers
- École Polytechnique Fédérale de LausanneCH19 papers
- Stefan Meyer Institute for Subatomic PhysicsAT18 papers
- Technical University of MunichDE17 papers
- Horia Hulubei National Institute for R and D in Physics and Nuclear EngineeringRO16 papers
- University of TriesteIT16 papers
- Université de RennesFR15 papers
- Sapienza University of RomeIT14 papers
613 papers
Bio-Inspired Palette Evolution in Indirectly Encoded Substrates: Timescale Compatibility Shapes Activation Function Discovery
Romain Claret, Michael O'Neill, Paul Cotofrei +1
Indirectly encoded neural networks can assign different activation functions to individual nodes, but the right functions are rarely known in advance. When the available set contai…
Per-Node Activation Function Evolution in Indirectly Encoded Substrates: Solvability, Limits, and Emergent Diversity
Romain Claret, Michael O'Neill, Paul Cotofrei +1
Biological neurons achieve computational diversity through specialized types: tonic, bursting, adapting, and fast-spiking cells coexist within the same circuit. Artificial neural n…
Multi-Behavioral Evolved Substrates Through Neuromodulation and Activation Selection
Romain Claret, Michael O'Neill, Paul Cotofrei +1
Open-ended artificial life systems must acquire diverse competencies from a single evolving genotype. Biological brains combine neuromodulation, which reconfigures circuits without…
Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
Romain Claret, Michael O'Neill, Paul Cotofrei +1
Neuroevolution of Augmenting Topologies (NEAT) and its advanced version, Evolvable-Substrate HyperNEAT (ES-HyperNEAT), have shown great potential in developing neural networks. How…
Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates
Romain Claret, Michael O'Neill, Paul Cotofrei +1
In neuroevolution, indirect encoding generates neural network connectivity from a compact genome rather than specifying each connection. ES-HyperNEAT automatically discovers where…
On Scaling Coordinate-Based Neuroevolution: The Quadtree Bottleneck in ES-HyperNEAT
Romain Claret, Michael O'Neill, Paul Cotofrei +1
ES-HyperNEAT evolves substrate topology through adaptive quadtree subdivision; to our knowledge, no implementation with full population-level GPU parallelization exists. We present…