HyperNEAT: Scaling Neuroevolution with Geometric Patterns
Learn about HyperNEAT's approach: using geometric patterns and indirect encoding to evolve complex neural architectures with biological regularities.
Gradient-Free-Optimization
2 posts tagged with gradient-free-optimization.
NEAT: Evolving Neural Network Topologies
Learn about NEAT's approach to evolving neural networks: automatic topology design, historical markings, and speciation for innovation protection.