Benchmarking The Generalization Capabilities Of A Compiling Genetic Programming System Using Sparse Data Sets

@inproceedings{Francone1996BenchmarkingTG,
  title={Benchmarking The Generalization Capabilities Of A Compiling Genetic Programming System Using Sparse Data Sets},
  author={Frank D. Francone and Peter Nordin and Wolfgang Banzhaf},
  year={1996}
}
Compili ng Genetic Programming Systems (‘CPGS’) are advanced evolutionary algor ithms that directly evolve RISC machine code. In this paper we compare the abili ty of CGPS to generalize with that of other machine learning (‘ML’) paradigms. This study presents our results on three classification problems. Our study involved 720 complete CGPS runs of population 3000 each, over 500 billi on fitness evaluations and 480 neural network runs as benchmarks. Our results were as follows: 1. When CGPS was… CONTINUE READING
27 Citations
14 References
Similar Papers

Citations

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

References

Publications referenced by this paper.
Showing 1-10 of 14 references

Designer and owner of Scientific Consultant Services, Inc., proprietor of N-Train neural network

  • J. Katz
  • 1996
Highly Influential
4 Excerpts

N-TRAIN Neural Network Development System, Users Manual, V

  • D. McCormick, J. Katz
  • 1992
Highly Influential
3 Excerpts

Explicitly Defined Introns and Destructive Crossover in Genetic Programming

  • J. P. Nordin, F. Francone, W. Banzhaf
  • Advances in Genetic Programming 2, K. Kinnear, Jr…
  • 1996

Advanced Algorithms for Neural Networks

  • T. Masters
  • 1995
3 Excerpts

Esprit Basic Research Project Number 6891, Document Number R3-B1-P

  • ELENA Partners, C. The. Jutten
  • Project Coordinator
  • 1995

Similar Papers

Loading similar papers…