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]

Authors

Bedri C. Cetin

This author has not been identified. Look up 'Bedri C. Cetin' in Google

Joel W. Burdick

This author has not been identified. Look up 'Joel W. Burdick' in Google

Jacob Barhen

This author has not been identified. Look up 'Jacob Barhen' in Google