Title :
The rule-extraction through the preimage analysis
Author :
Tsaih, Rua-Huan ; Wan, Yat-Wah ; Huang, Shin-Ying
Author_Institution :
Dept. of Manage. Inf. Syst., Nat. Chengchi Univ., Taipei
Abstract :
This study reveals the properties of the input/output relationship for a real-valued single-hidden layer feed-forward neural network (SLFN) with the tanh activation function on all hidden-layer nodes and the linear activation function on output node. Specifically, the rule-extraction of the SLFN is done through mathematically analyzing its preimage, which is the set of input values for a given output value.
Keywords :
feature extraction; feedforward neural nets; hidden-layer nodes; input-output relationship; linear activation function; preimage analysis; real-valued single-hidden layer feed-forward neural network; rule-extraction through; tanh activation function; Feedforward neural networks; Feedforward systems; Neural networks; Vectors; preimage; preimage analysis; single-hidden layer feed-forward neural network;
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2008.4633993
