Analysis of error landscapes in multi-layered neural networks for classification

@article{Rakitianskaia2016AnalysisOE,
  title={Analysis of error landscapes in multi-layered neural networks for classification},
  author={Anna S. Rakitianskaia and Eduan Bekker and Katherine Malan and Andries Petrus Engelbrecht},
  journal={2016 IEEE Congress on Evolutionary Computation (CEC)},
  year={2016},
  pages={5270-5277}
}
Artificial neural networks are inherently high-dimensional, which limits our ability to visualise and understand their inner workings. Neural network architecture and training algorithm parameters are usually optimised on an ad hoc basis, with very limited insight into the nature of the objective function landscape. This study proposes using fitness landscape analysis to quantify topological properties of neural network error landscapes. Five techniques from the fitness landscape analysis field… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 34 REFERENCES

A progressive random walk algorithm for sampling continuous fitness landscapes

——
  • Proceedings of the IEEE Congress on Evolutionary Computation. IEEE, 2014, pp. 2507–2514.
  • 2014
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…