State sampling dependence of the Hopfield network inference

Details State sampling dependence of the Hopfield network inference State sampling dependence of the Hopfield network inference

2011-04-26

arxiv.org/abs/1104.4931v2

Commun. Theor. Phys. 57 (2012) 169-172

Physics

Condensed Matter

Disordered Systems and Neural Networks

4 pages, 1 figure, further discussions added and relevant references added

Scientific paper

The fully connected Hopfield network is inferred based on observed magnetizations and pairwise correlations. We present the system in the glassy phase with low temperature and high memory load. We find that the inference error is very sensitive to the form of state sampling. When a single state is sampled to compute magnetizations and correlations, the inference error is almost indistinguishable irrespective of the sampled state. However, the error can be greatly reduced if the data is collected with state transitions. Our result holds for different disorder samples and accounts for the previously observed large fluctuations of inference error at low temperatures.

Affiliated with

Also associated with

No associations

Rating

State sampling dependence of the Hopfield network inference 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 State sampling dependence of the Hopfield network inference, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and State sampling dependence of the Hopfield network inference will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-296343