Evolutionary Design of Neural Network Architectures Using a Descriptive Encoding Language

@article{Jung2006EvolutionaryDO,
  title={Evolutionary Design of Neural Network Architectures Using a Descriptive Encoding Language},
  author={Jae-Yoon Jung and James A. Reggia},
  journal={IEEE Transactions on Evolutionary Computation},
  year={2006},
  volume={10},
  pages={676-688}
}
Evolutionary algorithms are a promising approach to the automated design of artificial neural networks, but they require a compact and efficient genetic encoding scheme to represent repetitive and recurrent modules in networks. We present a problem-independent approach based on a human-readable and writable descriptive encoding using a high-level language. This encoding is based on developmental methods and a modular neural network paradigm. Here, we show that our approach works effectively by… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 27 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 57 references

and R

  • M. Radio, J. Reggia
  • Berndt, “Learning word pronunciations using a…
  • 2001
Highly Influential
4 Excerpts

Evolving modular architectures for neural networks , ”

  • R. Calabretta Ferdinando, D. Parisi
  • Connectionist Models of Learning , Development…
  • 2004

Similar Papers

Loading similar papers…