neural networks research group
areas
people
projects
demos
publications
software/data
Hierarchical Evolution Of Neural Networks (1998)
David E. Moriarty
and
Risto Miikkulainen
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.
View:
PDF
,
PS
Citation:
In
Proceedings of the 1998 IEEE Conference on Evolutionary Computation (ICEC98)
, 428-433, Anchorage, AK, 1998. Piscataway, NJ: IEEE.
Bibtex:
@InProceedings{moriarty:icec98, title={Hierarchical Evolution Of Neural Networks}, author={David E. Moriarty and Risto Miikkulainen}, booktitle={Proceedings of the 1998 IEEE Conference on Evolutionary Computation (ICEC98)}, address={Anchorage, AK}, publisher={Piscataway, NJ: IEEE}, pages={428-433}, url="http://nn.cs.utexas.edu/?moriarty:icec98", year={1998} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
David E. Moriarty
Ph.D. Alumni
moriarty [at] alumni utexas net
Areas of Interest
Evolutionary Computation
Neuroevolution
Reinforcement Learning
Robotics
Applications