Fitness Landscape Analysis of Weight-Elimination Neural Networks

@article{Bosman2017FitnessLA,
  title={Fitness Landscape Analysis of Weight-Elimination Neural Networks},
  author={Anna Sergeevna Bosman and Andries Petrus Engelbrecht and Mard{\'e} Helbig},
  journal={Neural Processing Letters},
  year={2017},
  volume={48},
  pages={353-373}
}
Neural network architectures can be regularised by adding a penalty term to the objective function, thus minimising network complexity in addition to the error. However, adding a term to the objective function inevitably changes the surface of the objective function. This study investigates the landscape changes induced by the weight elimination penalty function under various parameter settings. Fitness landscape metrics are used to quantify and visualise the induced landscape changes, as well… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 48 REFERENCES

A Comprehensive Survey on Fitness Landscape Analysis

  • Recent Advances in Intelligent Engineering Systems
  • 2012
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Search space boundaries in neural network error landscape analysis

  • 2016 IEEE Symposium Series on Computational Intelligence (SSCI)
  • 2016
VIEW 3 EXCERPTS

Saturation in PSO neural network training: Good or evil?

  • 2015 IEEE Congress on Evolutionary Computation (CEC)
  • 2015
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…