Retrieval dynamics of neural networks for sparsely coded sequential patterns

Details Retrieval dynamics of neural networks for sparsely coded sequential patterns Retrieval dynamics of neural networks for sparsely coded sequential patterns

1998-05-12

arxiv.org/abs/cond-mat/9805135v2

J. Phys. A: Math. Gen. 31. L613-L620 (1998)

Physics

Condensed Matter

Disordered Systems and Neural Networks

9 pages including 4 EPSF figures, latex209, ref[21] is modefied

Scientific paper

10.1088/0305-4470/31/36/004

It is well known that a sparsely coded network in which the activity level is extremely low has intriguing equilibrium properties. In the present work, we study the dynamical properties of a neural network designed to store sparsely coded sequential patterns rather than static ones. Applying the theory of statistical neurodynamics, we derive the dynamical equations governing the retrieval process which are described by some macroscopic order parameters such as the overlap. It is found that our theory provides good predictions for the storage capacity and the basin of attraction obtained through numerical simulations. The results indicate that the nature of the basin of attraction depends on the methods of activity control employed. Furthermore, it is found that robustness against random synaptic dilution slightly deteriorates with the degree of sparseness.

Affiliated with

Also associated with

No associations

Rating

Retrieval dynamics of neural networks for sparsely coded sequential patterns does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Retrieval dynamics of neural networks for sparsely coded sequential patterns, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Retrieval dynamics of neural networks for sparsely coded sequential patterns will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-635790