Partially connected feedforward neural networks structured by input types

被引:19
作者
Kang, S [1 ]
Isik, C
机构
[1] Informat & Commun Univ, Lab Multimedia Comp Commun & Broadcasting, Taejon 305714, South Korea
[2] Syracuse Univ, Dept Elect Engn & Comp Sci, Syracuse, NY 13244 USA
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 2005年 / 16卷 / 01期
关键词
fully connected neural network (FCNN); input sensitivity; input type (IT); partially connected neural network (PCNN);
D O I
10.1109/TNN.2004.839353
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes, a,new method to model partially connected feedforward neural networks (PCFNNs) from the identified input type (IT) which refers to whether each input is coupled with or uncoupled from other inputs in generating output. The identification is done by analyzing input sensitivity changes as amplifying the magnitude of inputs. The sensitivity changes of the uncoupled inputs are not correlated with the variation on any other input, while those of the coupled inputs are correlated with the variation on any one of the coupled inputs. According to the identified ITs, a PCFNN can be structured. Each uncoupled input does not share the neurons in the hidden layer with other inputs in order to contribute to output in an independent manner, while the coupled inputs share the neurons with one another. After deriving the mathematical input sensitivity analysis for each IT, several experiments, as well as a real example (blood pressure (BP) estimation), are described to demonstrate how well our method works.
引用
收藏
页码:175 / 184
页数:10
相关论文
共 27 条
[1]  
[Anonymous], 1998, INTRO BOOTSTRAP
[2]  
Bates D.M., 1998, NONLINEAR REGRESSION
[3]  
Chen J, 2000, PROCEEDINGS OF THE 43RD IEEE MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS I-III, P248, DOI 10.1109/MWSCAS.2000.951631
[4]  
CHUNG YY, P ICSP 98, P506
[5]  
COHEN D, 1989, NEW DEVELOPMENTS IN NEURAL COMPUTING, P1
[6]   Neural network pruning with Tukey-Kramer multiple comparison procedure [J].
Duckro, DE ;
Quinn, DW ;
Gardner, SJ .
NEURAL COMPUTATION, 2002, 14 (05) :1149-1168
[7]  
Elizondo D, 1997, Int J Neural Syst, V8, P535, DOI 10.1142/S0129065797000513
[8]  
ELIZONDO D, 1995, P INT C NEUR NETW, P290
[9]  
FIESLER E, 1994, P INT C ART NEUR NET, P793
[10]  
Hassibi B., 1994, ADV NEURAL INFORMATI, V6, P263