DocumentCode :
1843045
Title :
Feedforward networks with monotone constraints
Author :
Zhang, Hong ; Zhang, Zhen
Volume :
3
fYear :
1999
fDate :
1999
Firstpage :
1820
Abstract :
In many practical applications of artificial neural networks (ANN), there exist natural constraints on the model such as monotonic relations between inputs and outputs that are known in advance. It is advantageous to incorporate these constraints into the ANN structure. We propose a modified feedforward network structure that enforces monotonic relations on designated input variables. The backpropagation formulas for the gradients in the new network structure are derived which lead to various learning algorithms. The monotone properties and the backpropagation formulas for the networks are proven mathematically and verified with numerical examples. A computer program for the new network structure and a learning algorithm is implemented to test the system. Experimental results are obtained on both simulated and real data sets
Keywords :
backpropagation; feedforward neural nets; ANN; artificial neural networks; back propagation; backpropagation; computer program; learning algorithms; modified feedforward network structure; monotone constraints; Artificial neural networks; Input variables; Multilayer perceptrons; Neural networks; Neurons; System testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
ISSN :
1098-7576
Print_ISBN :
0-7803-5529-6
Type :
conf
DOI :
10.1109/IJCNN.1999.832655
Filename :
832655
Link To Document :
بازگشت