By Topic

A bounded exploration approach to constructive algorithms for recurrent neural networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Bone, R. ; Lab. d''Inf., Ecole d''Ingenieurs en Inf. pour l''Ind., Tours, France ; Crucianu, M. ; Verley, G. ; Asselin de Beauville, J.-P.

When long-term dependencies are present in a time series, the approximation capabilities of recurrent neural networks are difficult to exploit by gradient descent algorithms. It is easier for such algorithms to find good solutions if one includes connections with time delays in the recurrent networks. One can choose the locations and delays for these connections by the heuristic presented. As shown on two benchmark problems, this heuristic produces very good results while keeping the total number of connections in the recurrent network to a minimum

Published in:

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on  (Volume:3 )

Date of Conference: