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.
Citation:
Shuxiang Xu, Ming Zhang, "Justification of a Neuron-Adaptive Activation Function," ijcnn, vol. 3, pp.3465, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3, 2000