neural networks research group
areas
people
projects
demos
publications
software/data
Culling And Teaching In Neuro-Evolution (1997)
Paul McQuesten
and
Risto Miikkulainen
The evolving population of neural nets contains information not only in terms of genes, but also in the collection of behaviors of the population members. Such information can be thought of as a kind of culture" of the population. Two ways of exploiting that culture are explored in this paper: (1) Culling overlarge litters: Generate a large number of offspring with different crossovers, quickly evaluate them by comparing their performance to the population, and throw away those that appear poor. (2) Teaching: Use backpropagation to train offspring toward the performance of the population. Both techniques result in faster, more effective neuro-evolution, and they can be effectively combined, as is demonstrated on the inverted pendulum problem. Additional methods of cultural exploitation are possible and will be studied in future work. These results suggest that cultural exploitation is a powerful idea that allows leveraging several aspects of the genetic algorithm.
View:
PDF
,
PS
Citation:
In Thomas B{"a}ck, editors,
Proceedings of the Seventh International Conference on Genetic Algorithms (ICGA-97, East Lansing, MI)
, 760-767, 1997. San Francisco, CA: Morgan Kaufmann.
Bibtex:
@InProceedings{mcquesten:icga9797, title={Culling And Teaching In Neuro-Evolution}, author={Paul McQuesten and Risto Miikkulainen}, booktitle={Proceedings of the Seventh International Conference on Genetic Algorithms (ICGA-97, East Lansing, MI)}, editor={Thomas B{"a}ck}, publisher={San Francisco, CA: Morgan Kaufmann}, pages={760-767}, url="http://nn.cs.utexas.edu/?mcquesten:icga97", year={1997} }
People
Paul H. McQuesten
Ph.D. Alumni
paul [at] mcquesten net
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Areas of Interest
Evolutionary Computation
Neuroevolution
Reinforcement Learning