Mixed states on neural network with structural learning

Details Mixed states on neural network with structural learning Mixed states on neural network with structural learning

2002-06-28

arxiv.org/abs/cond-mat/0206559v2

Physics

Condensed Matter

Disordered Systems and Neural Networks

15 pages, 7 figures

Scientific paper

We investigated the properties of mixed states in a sparsely encoded associative memory model with a structural learning method. When mixed states are made of s memory patterns, s types of mixed states, which become equilibrium states of the model, can be generated. To investigate the properties of s types of the mixed states, we analyzed them using the statistical mechanical method. We found that the storage capacity of the memory pattern and the storage capacity of only a particular mixed state diverge at the sparse limit. We also found that the threshold value needed to recall the memory pattern is nearly equal to the threshold value needed to recall the particular mixed state. This means that the memory pattern and the particular mixed state can be made to easily coexist at the sparse limit. The properties of the model obtained by the analysis are also useful for constructing a transform-invariant recognition model.

Affiliated with

Also associated with

No associations

Rating

Mixed states on neural network with structural learning 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 Mixed states on neural network with structural learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Mixed states on neural network with structural learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-645875