This work evolves, to the knowledge for the first time in indirect encoding, per-node activation function assignments from an 18-function palette across more than 4,500 experimental runs spanning Boolean logic, regression, and spatial classification.
Romain Claret, Michael O'Neill, Paul Cotofrei et al.· IEEE Symposium on Artificial...· 2 citations
This work designs 13 strategies (11 inspired by biological adaptation mechanisms, plus baseline and oracle controls) that modify the set of available activation functions during evolution, designing a biological principle into an evolutionary operator that translates a biological principle into an evolutionary operator...
Romain Claret, Michael O'Neill, Paul Cotofrei et al.· Lecture Notes in Computer Sc...· 1 citation
Most hyperparameter configurations for Evolvable-Substrate HyperNEAT (ES-HyperNEAT) produce networks that stagnate at random-guessing performance, wasting computational resources. We frame early stopping as binary classification on early fitness trajectories: for each trial, we compute the cumulative median of best-per...
Romain Claret, Arthur Gygax, Michael O'Neill et al.· 2 citations· ⚡1
Inspired by Mixture-of-Experts (MoE) principles, Evolvable-Substrate HyperNEAT is partitioned into non-overlapping spatial segments, each assigned to a separately evolved specialist network, which forces evolution to discover features across the entire image.
Romain Claret, Arthur Gygax, Michael O'Neill et al.· 2 citations
These findings define the structural constraints any substrate-discovery method must satisfy to scale coordinate-based neuroevolution; the companion EMR-HyperNEAT reformulation, which replaces adaptive subdivision with eager evaluation of a static multi-resolution grid, satisfies them and resolves the bottleneck this p...
Romain Claret, Michael O'Neill, Paul Cotofrei et al.· 0 citations
This study investigates the optimization of ES-HyperNEAT hyperparameters using the Tree-structured Parzen Estimator (TPE) on the MNIST classification task, exploring a search space of over 3 billion potential combinations and provides insights into the hyperparameters' transferability across tasks of varying complexity...
Romain Claret, Michael O'Neill, Paul Cotofrei et al.· GECCO Companion· 5 citations· ⚡1
This work presents Eager Multi-Resolution HyperNEAT (EMR-HyperNEAT), which reformulates adaptive substrate discovery as a batch tensor operation: shared position grids are precomputed for all depths, every position is evaluated in one vectorized CPPN call, then the same variance criterion filters the output.
Romain Claret, Michael O'Neill, Paul Cotofrei et al.· Proceedings of the Genetic a...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
