Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution
Evolvable-Substrate HyperNEAT (ES-HyperNEAT), a bio-inspired indirect encoding that determines neuron placement and connection weights from spatial coordinates, exhibits a failure mode on MNIST as a diagnostic benchmark. Because input pixels map to a coordinate space centered at the origin, evolved networks converge on a small central cluster of input pixels, a spatial-concentration bias; prior work observed only 21% mean accuracy in this regime. Is this bias an optimization artifact or an architectural ceiling? Inspired by Mixture-of-Experts (MoE) principles, we partition the input into non-o
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 47%The Emergent Symbolic Structure of Artificial Neural Networks →
- LinkedLinked via arxiv author · 85%Romain Claret →
“Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution”
- LinkedLinked via arxiv author · 85%Arthur Gygax →
“Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution”
- LinkedLinked via arxiv author · 85%Michael O'Neill →
“Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution”
- LinkedLinked via arxiv author · 85%Paul Cotofrei →
“Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution”
- LinkedLinked via arxiv author · 85%Michael Palma Mendes →
“Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution”
- LinkedLinked via arxiv author · 85%Pascal Felber →
“Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution”