Justification of a Neuron-Adaptive Activation Function

IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3 p. 3465
Justification of a Neuron-Adaptive Activation Function
Shuxiang Xu, University of Tasmania
Ming Zhang, University of Western Sydney Macarthur

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.861351
Send link to a friend

Abstract
An empirical justification of a neuron-adaptive activation function for feed-forward neural networks has been proposed in this paper. Simulation results reveal that feed-forward neural networks with the proposed neuron-adaptive activation function present several advantages over traditional neuron-fixed feed-forward networks such as increased flexibility, much reduced network size, faster learning, and lessened approximation errors.
Back to Top Additional Information
Citation: Shuxiang Xu, Ming Zhang, "Justification of a Neuron-Adaptive Activation Function," ijcnn, p. 3465, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3, 2000

	Advanced Search
CS Search Google Search