Title :
Justification of a neuron-adaptive activation function
Author :
Xu, Shuxiang ; Zhang, Ming
Author_Institution :
Sch. of Comput., Tasmania Univ., Hobart, Tas., Australia
Abstract :
An empirical justification of a neuron-adaptive activation function for feedforward neural networks has been proposed in this paper. Simulation results reveal that feedforward neural networks with the proposed neuron-adaptive activation function present several advantages over traditional neuron-fixed feedforward networks such as increased flexibility, much reduced network size, faster learning, and lessened approximation errors
Keywords :
feedforward neural nets; transfer functions; approximation errors; feedforward neural networks; flexibility; learning; neuron-adaptive activation function; Approximation error; Computational modeling; Computer networks; Electronic mail; Feedforward neural networks; Feedforward systems; Function approximation; Neural networks; Neurons; Spline;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.861351
