Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1996-10-22
Physics
Condensed Matter
Disordered Systems and Neural Networks
16 pages, Latex2e
Scientific paper
10.1103/PhysRevE.55.7369
We consider an ensemble of $K$ single-layer perceptrons exposed to random inputs and investigate the conditions under which the couplings of these perceptrons can be chosen such that prescribed correlations between the outputs occur. A general formalism is introduced using a multi-perceptron costfunction that allows to determine the maximal number of random inputs as a function of the desired values of the correlations. Replica-symmetric results for $K=2$ and $K=3$ are compared with properties of two-layer networks of tree-structure and fixed Boolean function between hidden units and output. The results show which correlations in the hidden layer of multi-layer neural networks are crucial for the value of the storage capacity.
Engel Assaf
Kanter Ido
Malzahn D.
No associations
LandOfFree
Storage capacity of correlated perceptrons 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 Storage capacity of correlated perceptrons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Storage capacity of correlated perceptrons will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-700787