Global descent replaces gradient descent to avoid local minima problem in learning with artificial neural networks

Bedri C. Cetin, Joel W. Burdick, Jacob Barhen. Global descent replaces gradient descent to avoid local minima problem in learning with artificial neural networks. In Proceedings of International Conference on Neural Networks (ICNN'88), San Francisco, CA, USA, March 28 - April 1, 1993. pages 836-842, IEEE, 1993. [doi]

@inproceedings{CetinBB93,
  title = {Global descent replaces gradient descent to avoid local minima problem in learning with artificial neural networks},
  author = {Bedri C. Cetin and Joel W. Burdick and Jacob Barhen},
  year = {1993},
  doi = {10.1109/ICNN.1993.298667},
  url = {https://doi.org/10.1109/ICNN.1993.298667},
  researchr = {https://researchr.org/publication/CetinBB93},
  cites = {0},
  citedby = {0},
  pages = {836-842},
  booktitle = {Proceedings of International Conference on Neural Networks (ICNN'88), San Francisco, CA, USA, March 28 - April 1, 1993},
  publisher = {IEEE},
}