DocumentCode
3248823
Title
The effect of the activation function of the back propagation algorithm
Author
Tepedelenlioglu, Nazif ; Rezgui, Ali
Author_Institution
Dept. of Electr. & Comput. Eng., Florida Inst. of Technol., Melbourne, FL, USA
fYear
1989
fDate
0-0 1989
Firstpage
139
Lastpage
142
Abstract
The effect is investigated of the activation function (the node nonlinearity) on the performance of the backpropagation algorithm in training a multilayer perceptron. Simulations for a two-layer neural net with two input nodes, a single output node, and eight nodes in the hidden layer are presented. The main conclusion presented is that the universally accepted smoothness condition for the nonlinearity is not necessary for the proper functioning of the algorithm.<>
Keywords
learning systems; neural nets; activation function; back propagation algorithm; multilayer perceptron; nonlinearity; smoothness condition; two-layer neural net; Learning systems; Neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Systems Engineering, 1989., IEEE International Conference on
Conference_Location
Fairborn, OH, USA
Type
conf
DOI
10.1109/ICSYSE.1989.48639
Filename
48639
Link To Document