On the Divergence Dynamics of the Nonlinear Line of Attraction
Ming-Jung Seow
Asari, V.K.
Old Dominion Univ., Norfolk;
This paper appears in: Neural Networks, 2006. IJCNN '06. International Joint Conference on
Publication Date: 0-0 0
On page(s): 3275-3278
Location: Vancouver, BC,
ISBN: 0-7803-9490-9
INSPEC Accession Number: 9723244
Digital Object Identifier: 10.1109/IJCNN.2006.247323
Current Version Published: 2006-10-30
Abstract
In designing a recurrent neural network, it is usually of prime importance to guarantee the convergence in the dynamics of the network. We propose to modify this picture: if the brain remembers by converging to the state representing familiar patterns, it should also diverge from such states when presented with an unknown encoded representation of a visual image. We propose to capture this behavior using a nonlinear line attractor network. This model encapsulates attractive fixed points scattered in the state space representing patterns with similar characteristics as an attractive curved line. The dynamics of the nonlinear line attractor network is designed such that when the network is able to reach equilibrium (stable), the input is considered as one of the stored patterns. Conversely, when the network is unable to reach equilibrium (unstable), the input is considered to be dissimilar to the stored patterns and therefore is considered as pattern of another class. Several experiments on benchmark problems have shown that the proposed model can be very useful for discriminating patterns.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
