Adaptive Epigenetic Neural Networks: A Biologically Inspired Proof-of-Concept for Neuroevolution

We propose a novel hybrid neuroevolutionary algorithm inspired by epigeneticsthat attempts to combine the best of natural selection and reinforcement learning.Traditional approaches like NEAT evolve topologies and weights. In this context,fixed topology refers to maintaining a constant network architecture across allindividuals, with only neuron-level parameters (biases and epigenetic scalars)subject to adaptation. Our method, the Adaptive Epigenetic Neural Network(AENN), keeps weights fixed and evolves neuron-local epigenetic scalars thatregulate activation strength. We demonstrate a proof-of-concept by achieving97.90% test average accuracy on the Wisconsin Breast Cancer dataset with asmall population of 30 individuals over 25 generations. This biologically inspiredmechanism may offer a scalable, interpretable method for evolving fixed-topologynetworks.