论文信息 - An activation function adapting training algorithm for sigmoidal feedforward networks

An activation function adapting training algorithm for sigmoidal feedforward networks

The universal approximation results for sigmoidal feedforward artificial neural networks do not recommend a preferred activation function. In this paper a new activation function adapting algorithm is proposed for sigmoidal feedforward neural network training. The algorithm is compared against the backpropagation algorithm on four function approximation tasks. The results demonstrate that the proposed algorithm can be an order of magnitude faster than the backpropagation algorithm.

Yogesh Singh | Pravin Chandra | Y. Singh | Pravin Chandra

[1] Yogesh Singh,et al. A case for the self-adaptation of activation functions in FFANNs , 2004, Neurocomputing.

[2] Edmondo Trentin,et al. Networks with trainable amplitude of activation functions , 2001, Neural Networks.

[3] Ken-ichi Funahashi,et al. On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[4] Kurt Hornik,et al. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[5] Y. Singh,et al. A class +1 sigmoidal activation functions for FFANNs , 2003 .

[6] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[7] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..