By Topic

Error Surface of 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
$31 $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

2 Author(s)
Manh Cong Phan ; Sch. of Electr. & Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA ; Hagan, M.T.

We found in previous work that the error surfaces of recurrent networks have spurious valleys that can cause significant difficulties in training these networks. Our earlier work focused on single-layer networks. In this paper, we extend the previous results to general layered digital dynamic networks. We describe two types of spurious valleys that appear in the error surfaces of these networks. These valleys are not affected by the desired network output (or by the problem that the network is trying to solve). They depend only on the input sequence and the architecture of the network. The insights gained from this analysis suggest procedures for improving the training of recurrent neural networks.

Published in:

Neural Networks and Learning Systems, IEEE Transactions on  (Volume:24 ,  Issue: 11 )