IEEE - Institute of Electrical and Electronics Engineers, Inc. - Global descent replaces gradient descent to avoid local minima problem in learning with artificial neural networks

Proceedings of 1993 IEEE International Conference on Neural Networks (ICNN '93)

Author(s): Cetin, B.C. ; Burdick, J.W. ; Barhen, J.
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 January 1993
Conference Location: San Francisco, CA, USA, USA
Conference Date: 28 March 1993
ISBN (Paper): 0-7803-0999-5
DOI: 10.1109/ICNN.1993.298667
Regular:

One of the fundamental limitations of artificial neural network learning by gradient descent is the susceptibility to local minima during training. A new approach to learning is presented in which... View More

Advertisement