The mutual information of a stochastic binary channel: validity of the Replica Symmetry Ansatz

Physics – Condensed Matter – Disordered Systems and Neural Networks

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Latex, 29 pages, 2 Encapsulated Post Script figures. To appear in Journal of Physics A

Scientific paper

10.1088/0305-4470/32/10/007

We calculate the mutual information (MI) of a two-layered neural network with noiseless, continuous inputs and binary, stochastic outputs under several assumptions on the synaptic efficiencies. The interesting regime corresponds to the limit where the number of both input and output units is large but their ratio is kept fixed at a value $\alpha$. We first present a solution for the MI using the replica technique with a replica symmetric (RS) ansatz. Then we find an exact solution for this quantity valid in a neighborhood of $\alpha = 0$. An analysis of this solution shows that the system must have a phase transition at some finite value of $\alpha$. This transition shows a singularity in the third derivative of the MI. As the RS solution turns out to be infinitely differentiable, it could be regarded as a smooth approximation to the MI. This is checked numerically in the validity domain of the exact solution.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

The mutual information of a stochastic binary channel: validity of the Replica Symmetry Ansatz 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 The mutual information of a stochastic binary channel: validity of the Replica Symmetry Ansatz, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The mutual information of a stochastic binary channel: validity of the Replica Symmetry Ansatz will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-597428

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.