neural networks research group
areas
people
projects
demos
publications
software/data
Evolving Populations Of Expert Neural Networks (2001)
Joseph Bruce
and
Risto Miikkulainen
In standard neuroevolution, the goal is to evolve one neural network that would compute the right answer most often. However, it often turns out that the population as a whole could perform even better, if we could only choose the right network for each input. One way to do this is to evolve networks that output not only the answer, but also an estimate of that answer's correctness. Experiments in the handwritten character recognition domain show that such an evolutionary process, combined with an effective technique for speciation, can create a population of networks that collectively performs better than any individual network.
View:
PDF
,
PS
Citation:
In
Proceedings of the Genetic and Evolutionary Computation Conference
, 251-257, San Francisco, CA, 2001. Morgan Kaufmann.
Bibtex:
@inproceedings{bruce:gecco01, title={Evolving Populations Of Expert Neural Networks}, author={Joseph Bruce and Risto Miikkulainen}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference}, address={San Francisco, CA}, publisher={Morgan Kaufmann}, pages={251-257}, url="http://nn.cs.utexas.edu/?bruce:gecco01", year={2001} }
People
Joseph Bruce
Former Ph.D. Student
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Areas of Interest
Evolutionary Computation
Neuroevolution
Reinforcement Learning