Acceleration Techniques for the Network Inversion Algorithm

Hiroyuki TAKIZAWA  Taira NAKAJIMA  Masaaki NISHI  Hiroaki KOBAYASHI  Tadao NAKAMURA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E82-D   No.2   pp.508-511
Publication Date: 1999/02/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Bio-Cybernetics and Neurocomputing
Keyword: 
multilayer perceptron,  network inversion algorithm,  active learning based on existing training examples,  classification problems,  

Full Text: PDF>>
Buy this Article




Summary: 
We apply two acceleration techniques for the backpropagation algorithm to an iterative gradient descent algorithm called the network inversion algorithm. Experimental results show that these techniques are also quite effective to decrease the number of iterations required for the detection of input vectors on the classification boundary of a multilayer perceptron.