Evolving neural networks using a dual representation with a combined crossover operator

@inproceedings{Pujol1998EvolvingNN,
  title={Evolving neural networks using a dual representation with a combined crossover operator},
  author={Carlos Figueira Pujol and Riccardo PoliAbstract},
  year={1998}
}
|In this paper a new approach to the evolution of neural networks is presented. A linear chromosome combined with a grid-based representation of the network, and a new crossover operator, allow the evolution of the architecture and the weights simultaneously. In our approach there is no need for a separate weight optimization procedure and networks with more than one type of activation function can be evolved. A pruning strategy is also introduced, which leads to the generation of solutions… CONTINUE READING
Highly Cited
This paper has 53 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.

Citations

Publications citing this paper.

53 Citations

0102030'99'03'08'13'18
Citations per Year
Semantic Scholar estimates that this publication has 53 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 23 references

Parallel distributed genetic programming

View 7 Excerpts
Highly Influenced

Evolution of the topology and the weights of neural networks using genetic programming with a dual representation," Technical report CSRP-97-07, The Uni- versity of Birmingham

J.C.F. Pujol, R. Poli
School of Computer Science, • 1997
View 4 Excerpts
Highly Influenced

A preliminary study on designing arti cial neural networks using co-evolution,

X. Yao, Y. Shi
Proceedings of the IEEE Singapore International Conference on Intelligent Control and Instrumentation, • 1995
View 4 Excerpts
Highly Influenced

Evolving neural network con- nectivity,

J. McDonnell, D. Waagen
Proceedings of IEEE International Conference on Neural Networks (ICNN), (San francisco, CA, • 1993
View 4 Excerpts
Highly Influenced

A new combined crossover operator to evolve the topology and the weights of neural networks us- ing a dual representation,

J.C.F. Pujol, R. Poli
Technical report CSRP-97-12, • 1997
View 1 Excerpt

Genetic structure for NN topology and weights optimization," in Proceedings of the International Conference on Genetic Algorithms in Engineering Systems: innovations and applications (GALESIA)

K. Tang, C. Chan, K. Man, S. Kwong
1995
View 2 Excerpts