Hierarchical evolution of neural networks

Abstract

In most applications of neuro-evolution, each individual in the population represents a complete neural network. Recent work on the SANE system, however, has demonstrated that evolving individual neurons often produces a more efficient genetic search. This paper demonstrates that while SANE can solve easy tasks very quickly, it often stalls in larger problems. A hierarchical approach to neuro-evolution is presented that overcomes SANE's difficulties by integrating both a neuron-level exploratory search and a network-level exploitive search. In a robot arm manipulation task, the hierarchical approach outperforms both a neuron-based search and a network-based search.