Thermodynamics of fully connected Blume-Emery-Griffiths neural networks

Details Thermodynamics of fully connected Blume-Emery-Griffiths neural networks Thermodynamics of fully connected Blume-Emery-Griffiths neural networks

2002-10-10

arxiv.org/abs/cond-mat/0210237v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

13 pages, 6 figures, iopart style

Scientific paper

10.1088/0305-4470/36/2/301

The thermodynamic and retrieval properties of fully connected Blume-Emery-Griffiths networks, storing ternary patterns, are studied using replica mean-field theory. Capacity-temperature phase diagrams are derived for several values of the pattern activity. It is found that the retrieval phase is the largest in comparison with other three-state neuron models. Furthermore, the meaning and stability of the so-called quadrupolar phase is discussed as a function of both the temperature and the pattern activity. Where appropriate, the results are compared with the diluted version of the model.

Affiliated with

Also associated with

No associations

Rating

Thermodynamics of fully connected Blume-Emery-Griffiths neural networks 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 Thermodynamics of fully connected Blume-Emery-Griffiths neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Thermodynamics of fully connected Blume-Emery-Griffiths neural networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-542296