Optimally adapted multi-state neural networks trained with noise

Details Optimally adapted multi-state neural networks trained with noise Optimally adapted multi-state neural networks trained with noise

1998-10-20

arxiv.org/abs/cond-mat/9810254v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

22 pages, 5 figures, accepted for publication in PRE

Scientific paper

10.1103/PhysRevE.59.947

The principle of adaptation in a noisy retrieval environment is extended here to a diluted attractor neural network of Q-state neurons trained with noisy data. The network is adapted to an appropriate noisy training overlap and training activity which are determined self-consistently by the optimized retrieval attractor overlap and activity. The optimized storage capacity and the corresponding retriever overlap are considerably enhanced by an adequate threshold in the states. Explicit results for improved optimal performance and new retriever phase diagrams are obtained for Q=3 and Q=4, with coexisting phases over a wide range of thresholds. Most of the interesting results are stable to replica-symmetry-breaking fluctuations.

Affiliated with

Also associated with

No associations

Rating

Optimally adapted multi-state neural networks trained with noise 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 Optimally adapted multi-state neural networks trained with noise, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimally adapted multi-state neural networks trained with noise will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-373210