Inproceedings,

Hierarchical Evolution of Neural Networks

, and .
Proceedings of the 1998 IEEE World Congress on Computational Intelligence, page 428--433. Anchorage, Alaska, USA, IEEE Press, (5-9 May 1998)

Abstract

In most applications of neuro-evolution, each individual in the population represents a complete neural network. Retent 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 difficul ties 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.

Tags

Users

  • @schaul
  • @brazovayeye
  • @idsia

Comments and Reviews