toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Record Links
Author Henriquez, P.A.; Ruz, G.A. pdf  doi
openurl 
  Title A non-iterative method for pruning hidden neurons in neural networks with random weights Type
  Year 2018 Publication Applied Soft Computing Abbreviated Journal Appl. Soft. Comput.  
  Volume 70 Issue Pages 1109-1121  
  Keywords Non -iterative learning; Neural networks; Random weights; Garson's algorithm; Pruning; Regression; Classification  
  Abstract Neural networks with random weights have the advantage of fast computational time in both training and testing. However, one of the main challenges of single layer feedforward neural networks is the selection of the optimal number of neurons in the hidden layer, since few/many neurons lead to problems of underfitting/overfitting. Adapting Garson's algorithm, this paper introduces a new efficient and fast non-iterative algorithm for the selection of neurons in the hidden layer for randomization based neural networks. The proposed approach is divided into three steps: (1) train the network with h hidden neurons, (2) apply Garson's algorithm to the matrix of the hidden layer, and (3) perform pruning reducing hidden layer neurons based on the harmonic mean. Our experiments in regression and classification problems confirmed that the combination of the pruning technique with these types of neural networks improved their predictive performance in terms of mean square error and accuracy. Additionally, we tested our proposed pruning method with neural networks trained under sequential learning algorithms, where Random Vector Functional Link obtained, in general, the best predictive performance compared to online sequential versions of extreme learning machines and single hidden layer neural network with random weights. (C) 2018 Elsevier B.V. All rights reserved.  
  Address [Henriquez, Pablo A.; Ruz, Gonzalo A.] Univ Adolfo Ibanez, Fac Ingn & Ciencias, Ave Diagonal Las Torres 2640, Santiago, Chile, Email: pabhenriquez@alumnos.uai.cl;  
  Corporate Author Thesis  
  Publisher Elsevier Science Bv Place of Publication Editor  
  Language English Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 1568-4946 ISBN Medium  
  Area Expedition Conference  
  Notes WOS:000443296000077 Approved  
  Call Number UAI @ eduardo.moreno @ Serial (down) 912  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: