Information and Topology in Attractor Neural Network

Details Information and Topology in Attractor Neural Network Information and Topology in Attractor Neural Network

2005-06-21

arxiv.org/abs/cond-mat/0506535v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

7 pgs., 5 figs

Scientific paper

A wide range of networks, including small-world topology, can be modelled by the connectivity $\gamma$, and randomness $\omega$ of the links. Both learning and attractor abilities of a neural network can be measured by the mutual information (MI), as a function of the load rate and overlap between patterns and retrieval states. We use MI to search for the optimal topology, for storage and attractor properties of the network. We find that, while the largest storage implies an optimal $MI(\gamma,\omega)$ at $\gamma_{opt}(\omega)\to 0$, the largest basin of attraction leads to an optimal topology at moderate levels of $\gamma_{opt}$, whenever $0\leq\omega<0.3$. This $\gamma_{opt}$ is related to the clustering and path-length of the network. We also build a diagram for the dynamical phases with random and local initial overlap, and show that very diluted networks lose their attractor ability.

Affiliated with

Also associated with

No associations

Rating

Information and Topology in Attractor Neural Network 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 Information and Topology in Attractor Neural Network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Information and Topology in Attractor Neural Network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-293117