Graph View

Weight Agnostic Neural Networks

1 min read

year: 2019
paper: https://arxiv.org/pdf/1906.04358
website: https://weightagnostic.github.io/
code:
connections: david ha


Activation functions (chosen from a fixed set) + topology are evolved via NEAT
Weights are shared (and fixed) across all connections.



Backlinks

  • Learning to Act through Evolution of Neural Diversity in Random Neural Networks

Created with Quartz v4.5.2 © 2026